Tarea 8 y 9_Ricardo Zamora Mennigke_Mineria de Datos I
Ricardo Zamora Mennigke
5/27/2020
#Tarea 08 y 09 #Mineria de Datos I #Ricardo Zamora Mennigke
library(tidyverse)## -- Attaching packages ------------------------------------------------------------------------------------------------------ tidyverse 1.3.0 --## v ggplot2 3.3.0 v purrr 0.3.3
## v tibble 2.1.3 v dplyr 0.8.5
## v tidyr 1.0.2 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.5.0## -- Conflicts --------------------------------------------------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(ggplot2)
library(dplyr)
library(glue)##
## Attaching package: 'glue'## The following object is masked from 'package:dplyr':
##
## collapselibrary(scales)##
## Attaching package: 'scales'## The following object is masked from 'package:purrr':
##
## discard## The following object is masked from 'package:readr':
##
## col_factorlibrary(xgboost)##
## Attaching package: 'xgboost'## The following object is masked from 'package:dplyr':
##
## slicelibrary(randomForest)## randomForest 4.6-14## Type rfNews() to see new features/changes/bug fixes.##
## Attaching package: 'randomForest'## The following object is masked from 'package:dplyr':
##
## combine## The following object is masked from 'package:ggplot2':
##
## marginPregunta 1: Suponga que trabajamos para un banco y se nos pide predecir el monto promedio de deuda en tarjeta de cr´edito de una cartera de clientes relativamente nuevos, basado en otra cartera de comportamiento y estructura similar de la cual s´ı se tiene informaci´on de deuda en tarjeta de cr´edito. En este ejercicio hacemos uso de la tabla de datos DeudaCredito.csv que contiene informaci´on de los clientes en una de las principales carteras de cr´edito del banco, e incluye variables que describen cada cliente tanto dentro del banco como fuera de ´este. Esta tabla de datos contiene 400 clientes y 11 variables que los describen. Seguidamente se explican las variables que conforman la tabla.
setwd("C:/Users/rzamoram/Documents/Machine Learning/Mineria de Datos I/Clase8")
datos<-read.csv("DeudaCredito.csv",dec='.',header=T)
str(datos)## 'data.frame': 400 obs. of 12 variables:
## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Ingreso : num 14.9 106 104.6 148.9 55.9 ...
## $ Limite : int 3606 6645 7075 9504 4897 8047 3388 7114 3300 6819 ...
## $ CalifCredit: int 283 483 514 681 357 569 259 512 266 491 ...
## $ Tarjetas : int 2 3 4 3 2 4 2 2 5 3 ...
## $ Edad : int 34 82 71 36 68 77 37 87 66 41 ...
## $ Educacion : int 11 15 11 11 16 10 12 9 13 19 ...
## $ Genero : Factor w/ 2 levels "Femenino","Masculino": 2 1 2 1 2 2 1 2 1 1 ...
## $ Estudiante : Factor w/ 2 levels "No","Si": 1 2 1 1 1 1 1 1 1 2 ...
## $ Casado : int 1 1 0 0 1 0 0 0 0 1 ...
## $ Etnicidad : Factor w/ 3 levels "Afrodescendiente",..: 3 2 2 2 3 3 1 2 3 1 ...
## $ Balance : int 333 903 580 964 331 1151 203 872 279 1350 ...suppressMessages(suppressWarnings(library(FactoMineR)))
suppressMessages(suppressWarnings(library(car)))
Atipicos<-(Boxplot(~Balance, data=datos, id.method="y",col="Blue")) #Monto promedio de deuda en tarjeta de cr´edito del cliente, en d´olares
Atipicos<-(Boxplot(~Ingreso, data=datos, id.method="y",col="Blue")) #Ingreso: Ingreso del cliente, en miles de d´olares.
Atipicos<-(Boxplot(~CalifCredit, data=datos, id.method="y",col="Blue")) #Ingreso: Ingreso del cliente, en miles de d´olares.
# Elimino variables categóricas
datos2 <- datos[,-c(1,8,9,11)] ##verificar correlaciones con variables numericas
head(datos2)## Ingreso Limite CalifCredit Tarjetas Edad Educacion Casado Balance
## 1 14.891 3606 283 2 34 11 1 333
## 2 106.025 6645 483 3 82 15 1 903
## 3 104.593 7075 514 4 71 11 0 580
## 4 148.924 9504 681 3 36 11 0 964
## 5 55.882 4897 357 2 68 16 1 331
## 6 80.180 8047 569 4 77 10 0 1151library(corrplot)## corrplot 0.84 loadedmatriz.correlacion<-cor(datos2)
corrplot(matriz.correlacion)
Debe tenerse en cuenta que aqui se denota unicamente un punto de vista inicial al eliminar variables categoricas y respuesta para analizar si existe cierta correlacion entre variables, sirve como un punto de vista inicial, para ver si pueden existir ciertos problemas de estimacion. Se puede observar que las variables predictoras Ingreso, Limite y Calificacion, estan significativamente correlacionadas con la variable de respuesta, es decir, en otros casos podrian agruparse como una sola variable. Esto es un indicativo de que al estimar las variables puedan comprometer la estimacion por lo que se debe tomar al analizar la respuesta y el resultado final del modelo.
muestra <- sample(1:nrow(datos),floor(nrow(datos)*0.20))
ttesting <- datos[muestra,]
taprendizaje <- datos[-muestra,]
nrow(ttesting)## [1] 80nrow(taprendizaje)## [1] 320- Basado en las estad´ısticas b´asicas explique cu´al variable num´erica parece ser la mejor para predecir la deuda en tarjeta de cr´etido.
summary(datos)## X Ingreso Limite CalifCredit
## Min. : 1.0 Min. : 10.35 Min. : 855 Min. : 93.0
## 1st Qu.:100.8 1st Qu.: 21.01 1st Qu.: 3088 1st Qu.:247.2
## Median :200.5 Median : 33.12 Median : 4622 Median :344.0
## Mean :200.5 Mean : 45.22 Mean : 4736 Mean :354.9
## 3rd Qu.:300.2 3rd Qu.: 57.47 3rd Qu.: 5873 3rd Qu.:437.2
## Max. :400.0 Max. :186.63 Max. :13913 Max. :982.0
## Tarjetas Edad Educacion Genero Estudiante
## Min. :1.000 Min. :23.00 Min. : 5.00 Femenino :207 No:360
## 1st Qu.:2.000 1st Qu.:41.75 1st Qu.:11.00 Masculino:193 Si: 40
## Median :3.000 Median :56.00 Median :14.00
## Mean :2.958 Mean :55.67 Mean :13.45
## 3rd Qu.:4.000 3rd Qu.:70.00 3rd Qu.:16.00
## Max. :9.000 Max. :98.00 Max. :20.00
## Casado Etnicidad Balance
## Min. :0.0000 Afrodescendiente: 99 Min. : 0.00
## 1st Qu.:0.0000 Asiatico :102 1st Qu.: 68.75
## Median :1.0000 Caucasico :199 Median : 459.50
## Mean :0.6125 Mean : 520.01
## 3rd Qu.:1.0000 3rd Qu.: 863.00
## Max. :1.0000 Max. :1999.00La mejor variable numerica para predecir la deuda en la tarjeta de credito es justamente la variable balance, ya que indica el Monto promedio de deuda en tarjeta de cr´edito del cliente, en d´olares. Dependiendo del estudio podria tambien ser interesante analizar la generacion de la calificacion crediticia pero esta es una calificacion que no
- Genere un modelo de regresi´on lineal m´ultiple incluyendo las todas las variables predictoras. ¿Cu´ales coeficientes obtiene para los β? D´e una interpretaci´on de 3 de los coeficientes que se obtienen en el modelo. ¿Cu´al variable parece tener m´as impacto sobre la variable a predecir y por qu´e?
modelo <- lm(Balance ~ ., data = datos)
modelo ##
## Call:
## lm(formula = Balance ~ ., data = datos)
##
## Coefficients:
## (Intercept) X Ingreso Limite
## -496.62039 0.04105 -7.80740 0.19052
## CalifCredit Tarjetas Edad Educacion
## 1.14249 17.83639 -0.62955 -1.09831
## GeneroMasculino EstudianteSi Casado EtnicidadAsiatico
## 9.54615 426.16715 -8.78055 16.85752
## EtnicidadCaucasico
## 9.29289summary(modelo)##
## Call:
## lm(formula = Balance ~ ., data = datos)
##
## Residuals:
## Min 1Q Median 3Q Max
## -166.48 -77.62 -14.37 56.21 316.52
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -496.62039 36.51325 -13.601 < 2e-16 ***
## X 0.04105 0.04343 0.945 0.3452
## Ingreso -7.80740 0.23431 -33.321 < 2e-16 ***
## Limite 0.19052 0.03279 5.811 1.3e-08 ***
## CalifCredit 1.14249 0.49100 2.327 0.0205 *
## Tarjetas 17.83639 4.34324 4.107 4.9e-05 ***
## Edad -0.62955 0.29449 -2.138 0.0332 *
## Educacion -1.09831 1.59817 -0.687 0.4924
## GeneroMasculino 9.54615 9.98431 0.956 0.3396
## EstudianteSi 426.16715 16.73077 25.472 < 2e-16 ***
## Casado -8.78055 10.36758 -0.847 0.3976
## EtnicidadAsiatico 16.85752 14.12112 1.194 0.2333
## EtnicidadCaucasico 9.29289 12.24194 0.759 0.4483
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 98.8 on 387 degrees of freedom
## Multiple R-squared: 0.9552, Adjusted R-squared: 0.9538
## F-statistic: 687.7 on 12 and 387 DF, p-value: < 2.2e-16Usando todos los datos se pueden sacar conclusiones al modelo mostrado abajo con solo training. En este caso los valores de β son los estimadores (estimate) del modelo. Aqui debe tenerse en cuenta que el modelo sin reducir seria: y = -496.62039 + 0.04105X - 7.80740 * Ingreso + … + 9.29289 * EtnicidadCaucasico Tomando como principal criterio las probabilidades existen varias variables que resultan significativas para la variable de respuesta especialmente el ingreso y si es Estdudiante. Es curioso ya que el t valor muestra un valor negativo igual que el estimador lo que indica que entre mayor ingreso menor problema crediticio. Contrario si es EstudianteSI esta variable tiene el mayor impacto, ya que si es estudiante su deuda aumenta segun el estimador 426.16715. Interpretando 3 coeficientes como ejemplo, por cada aumento en una unidad de Ingreso (en miles de dolares) la deuda en tarjeta de credito de la persona se reduce en 7,80740 dolares. Por cada tarjeta de credito adicional (Tarjetas) se estima que la persona tiene 17,83639 dolares mas un su monto de deuda en su tarjeta de credito. Finalmente por cada ano adicional en la edad del cliente se estima que su deuda es -0.62955 dolares mas baja.
# Calcula el modelo usando solo los datos de training
modelo.lm <- lm(Balance~., data = taprendizaje)
modelo.lm##
## Call:
## lm(formula = Balance ~ ., data = taprendizaje)
##
## Coefficients:
## (Intercept) X Ingreso Limite
## -503.0591 0.0123 -7.9026 0.2009
## CalifCredit Tarjetas Edad Educacion
## 1.0252 17.4851 -0.6203 -0.9079
## GeneroMasculino EstudianteSi Casado EtnicidadAsiatico
## 11.7868 442.5138 -7.7921 21.3282
## EtnicidadCaucasico
## 11.3099- ¿Qu´e error se obtiene sobre la tabla de testing para el modelo de regresi´on lineal? Interprete las medidas de error obtenidas.
# Residual Sum of Square (RSS)
RSS <- function(Pred,Real) {
ss <- sum((Real-Pred)^2)
return(ss)
}
# NumPred es el número total de predictores por eso se resta 1 (que es realidad sumar 1)
RSE<-function(Pred,Real,NumPred) {
N<-length(Real)-NumPred-1 # <- length(Real)-(NumPred+1)
ss<-sqrt((1/N)*RSS(Pred,Real))
return(ss)
}
MSE <- function(Pred,Real) {
N<-length(Real)
ss<-(1/N)*RSS(Pred,Real)
return(ss)
}
error.relativo <- function(Pred,Real) {
ss<-sum(abs(Real-Pred))/sum(abs(Real))
return(ss)
}
# Funciones para desplegar precisión
indices.precision <- function(real, prediccion,cantidad.variables.predictoras) {
return(list(error.cuadratico = MSE(prediccion,real),
raiz.error.cuadratico = RSE(prediccion,real,cantidad.variables.predictoras),
error.relativo = error.relativo(prediccion,real),
correlacion = as.numeric(cor(prediccion,real))))
}
# Gráfico de dispersión entre el valor real de la variable a predecir y la predicción del modelo.
plot.real.prediccion <- function(real, prediccion, modelo = "") {
g <- ggplot(data = data.frame(Real = real, Prediccion = as.numeric(prediccion)), mapping = aes(x = Real, y = Prediccion)) +
geom_point(size = 1, col = "dodgerblue3") +
labs(title = paste0("Real vs Predicción", ifelse(modelo == "", "", paste(", con", modelo))),
x = "Real",
y = "Predicción")
return(g)
}numero.predictoras <- dim(datos)[2] - 1
# Hace la Predicción
prediccion <- predict(modelo.lm, ttesting)
# Medición de precisión
pre.lm <- indices.precision(ttesting$Balance, prediccion,numero.predictoras)
pre.lm## $error.cuadratico
## [1] 11379.65
##
## $raiz.error.cuadratico
## [1] 115.7057
##
## $error.relativo
## [1] 0.1717528
##
## $correlacion
## [1] 0.9707004Medida de error en este caso se mide facilmente por la raiz del error cuadratico medio en terminos podria decirse para este caso mas “netos”. Ya que lo que indica este coeficiente es que la estimacion del modelo tiene un error absoluto estimado de + (mas) o (-) 94.58605 dolares en la estimacion final del Balance de la deuda en tarjetas de credito. El error relativo indica que el error de estimacion es aproximado de 12,68% y ademas la correlacion entre el valor real y el valor predicho es 0.9842869, es decir entre mas cercano a 1 mejor. En terminos generales la estimacion pues no es ideal pero tiene una estimacion predicha bastante significativamente precisa. Viendo de hecho la grafica Real vs Prediccion se denota que el modelo se ajusta bien a la funcion identidad, dando en realidad problemas en las estimaciones de clientes con deudas bajas o nulas, relacionado al residual standard error en 98,8.
# Gráfico real vs predicción, con curva de mejor ajuste lineal
g <- plot.real.prediccion(ttesting$Balance, prediccion, modelo = "Regresión Lineal")
g + geom_smooth(method = lm, size = 0.4, color = "red", se = FALSE)## `geom_smooth()` using formula 'y ~ x'
prediccion <- predict(modelo,datos, interval="confidence")
hist(prediccion, col = "green")
- Si tuviera que eliminar alguna o algunas de las variables con la esperanza de que mejore la predicci´on ¿Cu´al o cu´ales de las variables eliminar´ıa? ¿El nuevo modelo mejora la predicci´on?
Eliminaria del modelo X, Educacion, Genero, casado, etnicidad. solo dejaria Ingreso, Limite, CalifCredit, Tarjetas, Edad y Estudiante, ya que mostrar significancia para predecir la variable en estudio.
modelo <- lm(Balance ~ Ingreso + Limite + CalifCredit + Tarjetas + Edad + Estudiante, data = datos)
modelo##
## Call:
## lm(formula = Balance ~ Ingreso + Limite + CalifCredit + Tarjetas +
## Edad + Estudiante, data = datos)
##
## Coefficients:
## (Intercept) Ingreso Limite CalifCredit Tarjetas
## -493.7342 -7.7951 0.1937 1.0912 18.2119
## Edad EstudianteSi
## -0.6241 425.6099modelo <- lm(Balance ~ Ingreso + Limite + CalifCredit + Tarjetas + Edad + Estudiante, data = datos)
numero.predictoras <- dim(datos)[2] - 1
# Hace la Predicción
prediccion <- predict(modelo, ttesting)
# Medición de precisión
pre.lm <- indices.precision(ttesting$Balance, prediccion,numero.predictoras)
pre.lm## $error.cuadratico
## [1] 11005.44
##
## $raiz.error.cuadratico
## [1] 113.7874
##
## $error.relativo
## [1] 0.1675667
##
## $correlacion
## [1] 0.9713879La estimacion del modelo reducido tiene un error absoluto estimado de + (mas) o (-) 87.20528 dolares, inferior 94.58605 dolares en la estimacion final del Balance de la deuda en tarjetas de credito en el modelo completo, esto se explica porque al incluirse variables solo significativas el modelo no genera overfitting y permite eliminar variables que no aportan a la estimacion. El error relativo indica que el error de estimacion es aproximado de 11,48%, respecto al 12,68% y ademas la correlacion entre el valor real y el valor predicho es 0.9859838, respecto a 0.9842869, es decir, el modelo reducido se desmpena mejor.
# Gráfico real vs predicción, con curva de mejor ajuste lineal
g <- plot.real.prediccion(ttesting$Balance, prediccion, modelo = "Regresión Lineal")
g + geom_smooth(method = lm, size = 0.4, color = "red", se = FALSE)## `geom_smooth()` using formula 'y ~ x'
Pregunta 2: Un cliente nos contrata para estudiar una posible oportunidad de negocio, y para ver si le es rentable quiere una predicci´on de las ventas potenciales de asientos de ni˜nos para autos en su tienda. Para ello hacemos uso de los datos AsientosNinno.csv los cual contienen detalles de ventas de asientos de ni˜nos para auto en una serie de tiendas similares a las del cliente, y adem´as los datos incluyen variables que definen caracter´ısticas de la tienda y su localidad. La tabla de datos est´a formada por 400 filas y 11 columnas. Seguidamente se explican las variables que conforman la tabla.
- Cargue la tabla de datos en R. En caso de ser necesario, recodificar las variables de forma adecuada. Seleccione la variable a predecir, y para medir el error tome un 15 % de la tabla de datos.
setwd("C:/Users/rzamoram/Documents/Machine Learning/Mineria de Datos I/Clase8")
datos<-read.csv("AsientosNinno.csv",sep=';',dec='.',header=T)
str(datos)## 'data.frame': 400 obs. of 12 variables:
## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Ventas : num 9.5 11.22 10.06 7.4 4.15 ...
## $ PrecioCompt : int 138 111 113 117 141 124 115 136 132 132 ...
## $ Ingreso : int 73 48 35 100 64 113 105 81 110 113 ...
## $ Publicidad : int 11 16 10 4 3 13 0 15 0 0 ...
## $ Poblacion : int 276 260 269 466 340 501 45 425 108 131 ...
## $ Precio : int 120 83 80 97 128 72 108 120 124 124 ...
## $ CalidadEstant: Factor w/ 3 levels "Bueno","Malo",..: 2 1 3 3 2 2 3 1 3 3 ...
## $ Edad : int 42 65 59 55 38 78 71 67 76 76 ...
## $ Educacion : int 17 10 12 14 13 16 15 10 10 17 ...
## $ Urbano : int 1 1 1 1 1 0 1 1 0 0 ...
## $ USA : int 1 1 1 1 0 1 0 1 0 1 ...suppressMessages(suppressWarnings(library(FactoMineR)))
suppressMessages(suppressWarnings(library(car)))
Atipicos<-(Boxplot(~Ventas, data=datos, id.method="y",col="Blue")) #Monto promedio de deuda en tarjeta de cr´edito del cliente, en d´olares
# Elimino variables categóricas
datos2 <- datos[,-c(1,8)] ##verificar correlaciones con variables numericas
head(datos2)## Ventas PrecioCompt Ingreso Publicidad Poblacion Precio Edad Educacion Urbano
## 1 9.50 138 73 11 276 120 42 17 1
## 2 11.22 111 48 16 260 83 65 10 1
## 3 10.06 113 35 10 269 80 59 12 1
## 4 7.40 117 100 4 466 97 55 14 1
## 5 4.15 141 64 3 340 128 38 13 1
## 6 10.81 124 113 13 501 72 78 16 0
## USA
## 1 1
## 2 1
## 3 1
## 4 1
## 5 0
## 6 1library(corrplot)
matriz.correlacion<-cor(datos2)
corrplot(matriz.correlacion)
No hay mucha correlacion entre variables numericas predictoras.
muestra <- sample(1:nrow(datos),floor(nrow(datos)*0.15))
ttesting <- datos[muestra,]
taprendizaje <- datos[-muestra,]
nrow(ttesting)## [1] 60nrow(taprendizaje)## [1] 340- Aplique los modelos de regresi´on lineal m´ultiple, regresi´on Ridge y regresi´on Lasso incluyendo todas las variables predictoras. ¿Se anulan coeficientes para el caso de regresi´on Lasso?
En el caso de LASSO como se observara en la estimacion del punto 3, se eliminan PrecioCompt, Ingreso, Publicidad, Poblacion, CalidadEstantMedio, Edad, Educacion, Urbano y USA. Generan estimadores que aproximan a cero, dada la poca cantidad de variables que quedan, es bastante presumible que el caso ideal de Lasso optimo termine asemejando a una regresion clasica
- ¿Qu´e error se obtiene sobre la tabla de training para los 3 modelos generados anteriormente? ¿Cu´al considera que es el mejor seg´un la comparaci´on anterior?
Se aplican los modelos regresion lineal multiple, ridge y lasso, se generan varias simulaciones adicionales para mostrar un poco mas el comportamiento del lambda.
#Multiple
modelo <- lm(Ventas ~ ., data = datos)
modelo ##
## Call:
## lm(formula = Ventas ~ ., data = datos)
##
## Coefficients:
## (Intercept) X PrecioCompt Ingreso
## 10.5806217 -0.0003284 0.0930031 0.0156505
## Publicidad Poblacion Precio CalidadEstantMalo
## 0.1238581 0.0002157 -0.0953564 -4.8520250
## CalidadEstantMedio Edad Educacion Urbano
## -2.8941221 -0.0461835 -0.0224532 0.1278481
## USA
## -0.1853717summary(modelo)##
## Call:
## lm(formula = Ventas ~ ., data = datos)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.8409 -0.6817 0.0127 0.6468 3.4684
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10.5806217 0.6119800 17.289 < 2e-16 ***
## X -0.0003284 0.0004538 -0.724 0.470
## PrecioCompt 0.0930031 0.0041583 22.366 < 2e-16 ***
## Ingreso 0.0156505 0.0018582 8.422 7.3e-16 ***
## Publicidad 0.1238581 0.0111803 11.078 < 2e-16 ***
## Poblacion 0.0002157 0.0003708 0.582 0.561
## Precio -0.0953564 0.0026727 -35.678 < 2e-16 ***
## CalidadEstantMalo -4.8520250 0.1532252 -31.666 < 2e-16 ***
## CalidadEstantMedio -2.8941221 0.1309763 -22.097 < 2e-16 ***
## Edad -0.0461835 0.0031894 -14.480 < 2e-16 ***
## Educacion -0.0224532 0.0198208 -1.133 0.258
## Urbano 0.1278481 0.1132532 1.129 0.260
## USA -0.1853717 0.1499447 -1.236 0.217
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.02 on 387 degrees of freedom
## Multiple R-squared: 0.8736, Adjusted R-squared: 0.8697
## F-statistic: 222.9 on 12 and 387 DF, p-value: < 2.2e-16# Calcula el modelo usando solo los datos de training
modelo.lm <- lm(Ventas~., data = taprendizaje)
modelo.lm##
## Call:
## lm(formula = Ventas ~ ., data = taprendizaje)
##
## Coefficients:
## (Intercept) X PrecioCompt Ingreso
## 1.052e+01 -3.119e-04 9.286e-02 1.587e-02
## Publicidad Poblacion Precio CalidadEstantMalo
## 1.167e-01 9.516e-05 -9.386e-02 -4.819e+00
## CalidadEstantMedio Edad Educacion Urbano
## -2.915e+00 -4.467e-02 -3.756e-02 1.972e-01
## USA
## -9.165e-02numero.predictoras <- dim(datos)[2] - 1
# Hace la Predicción
prediccion <- predict(modelo.lm, ttesting)
# Medición de precisión
pre.lm <- indices.precision(ttesting$Ventas, prediccion,numero.predictoras)
pre.lm## $error.cuadratico
## [1] 1.477647
##
## $raiz.error.cuadratico
## [1] 1.359065
##
## $error.relativo
## [1] 0.1423242
##
## $correlacion
## [1] 0.9225625# Gráfico real vs predicción, con curva de mejor ajuste lineal
g <- plot.real.prediccion(ttesting$Ventas, prediccion, modelo = "Regresión Lineal")
g + geom_smooth(method = lm, size = 0.4, color = "red", se = FALSE)## `geom_smooth()` using formula 'y ~ x'
prediccion <- predict(modelo,datos, interval="confidence")
hist(prediccion, col = "green")
###Ridge
# La siguiente instrucción construye una matriz con los predictores
x<-model.matrix(Ventas~.,datos)
head(x)## (Intercept) X PrecioCompt Ingreso Publicidad Poblacion Precio
## 1 1 1 138 73 11 276 120
## 2 1 2 111 48 16 260 83
## 3 1 3 113 35 10 269 80
## 4 1 4 117 100 4 466 97
## 5 1 5 141 64 3 340 128
## 6 1 6 124 113 13 501 72
## CalidadEstantMalo CalidadEstantMedio Edad Educacion Urbano USA
## 1 1 0 42 17 1 1
## 2 0 0 65 10 1 1
## 3 0 1 59 12 1 1
## 4 0 1 55 14 1 1
## 5 1 0 38 13 1 0
## 6 1 0 78 16 0 1# Debemos eliminar la columna 1
x<-model.matrix(Ventas~.,datos)[,-c(1,2)]
head(x)## PrecioCompt Ingreso Publicidad Poblacion Precio CalidadEstantMalo
## 1 138 73 11 276 120 1
## 2 111 48 16 260 83 0
## 3 113 35 10 269 80 0
## 4 117 100 4 466 97 0
## 5 141 64 3 340 128 1
## 6 124 113 13 501 72 1
## CalidadEstantMedio Edad Educacion Urbano USA
## 1 0 42 17 1 1
## 2 0 65 10 1 1
## 3 1 59 12 1 1
## 4 1 55 14 1 1
## 5 0 38 13 1 0
## 6 0 78 16 0 1# La siguiente instrucción construye la variable a predecir
y<-datos$Ventaslibrary(glmnet)## Loading required package: Matrix##
## Attaching package: 'Matrix'## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack## Loaded glmnet 4.0ridge.mod<-glmnet(x,y,alpha=0)
dim(coef(ridge.mod))## [1] 12 100coef(ridge.mod)## 12 x 100 sparse Matrix of class "dgCMatrix"## [[ suppressing 100 column names 's0', 's1', 's2' ... ]]##
## (Intercept) 7.496325e+00 7.510538e+00 7.511918e+00 7.513432e+00
## PrecioCompt 1.192041e-38 2.931185e-05 3.219135e-05 3.535601e-05
## Ingreso 1.548850e-38 3.770975e-05 4.137451e-05 4.539416e-05
## Publicidad 1.156036e-37 2.812402e-04 3.085487e-04 3.384969e-04
## Poblacion 9.769243e-40 2.369954e-06 2.599362e-06 2.850801e-06
## Precio -5.360911e-38 -1.306493e-04 -1.433599e-04 -1.573041e-04
## CalidadEstantMalo -2.622818e-36 -6.391766e-03 -7.013581e-03 -7.695742e-03
## CalidadEstantMedio -4.235720e-37 -1.038898e-03 -1.140677e-03 -1.252478e-03
## Edad -4.081940e-38 -9.948302e-05 -1.091618e-04 -1.197800e-04
## Educacion -5.655718e-38 -1.374580e-04 -1.507909e-04 -1.654097e-04
## Urbano -9.633114e-38 -2.336091e-04 -2.562129e-04 -2.809854e-04
## USA 1.054415e-36 2.561941e-03 2.810361e-03 3.082723e-03
##
## (Intercept) 7.515093e+00 7.516913e+00 7.518910e+00 7.521098e+00
## PrecioCompt 3.883450e-05 4.265850e-05 4.686297e-05 5.148655e-05
## Ingreso 4.980280e-05 5.463778e-05 5.993993e-05 6.575397e-05
## Publicidad 3.713377e-04 4.073474e-04 4.468284e-04 4.901110e-04
## Poblacion 3.126349e-06 3.428275e-06 3.759052e-06 4.121376e-06
## Precio -1.726010e-04 -1.893813e-04 -2.077879e-04 -2.279772e-04
## CalidadEstantMalo -8.444076e-03 -9.264966e-03 -1.016540e-02 -1.115305e-02
## CalidadEstantMedio -1.375298e-03 -1.510237e-03 -1.658504e-03 -1.821433e-03
## Edad -1.314284e-04 -1.442064e-04 -1.582228e-04 -1.735970e-04
## Educacion -1.814369e-04 -1.990064e-04 -2.182644e-04 -2.393707e-04
## Urbano -3.081310e-04 -3.378723e-04 -3.704522e-04 -4.061350e-04
## USA 3.381306e-03 3.708598e-03 4.067317e-03 4.460429e-03
##
## (Intercept) 7.523498e+00 7.526128e+00 7.529010e+00 7.532169e+00
## PrecioCompt 5.657196e-05 6.216643e-05 6.832228e-05 7.509741e-05
## Ingreso 7.212877e-05 7.911776e-05 8.677935e-05 9.517733e-05
## Publicidad 5.375563e-04 5.895585e-04 6.465481e-04 7.089946e-04
## Poblacion 4.518180e-06 4.952655e-06 5.428271e-06 5.948793e-06
## Precio -2.501208e-04 -2.744064e-04 -3.010392e-04 -3.302441e-04
## CalidadEstantMalo -1.223628e-02 -1.342427e-02 -1.472707e-02 -1.615567e-02
## CalidadEstantMedio -2.000497e-03 -2.197318e-03 -2.413687e-03 -2.651582e-03
## Edad -1.904594e-04 -2.089531e-04 -2.292344e-04 -2.514745e-04
## Educacion -2.624995e-04 -2.878409e-04 -3.156020e-04 -3.460084e-04
## Urbano -4.452084e-04 -4.879851e-04 -5.348048e-04 -5.860359e-04
## USA 4.891171e-03 5.363069e-03 5.879968e-03 6.446051e-03
##
## (Intercept) 7.535631e+00 7.539423e+00 7.543576e+00 7.548125e+00
## PrecioCompt 8.255604e-05 9.076937e-05 9.981664e-05 1.097854e-04
## Ingreso 1.043814e-04 1.144674e-04 1.255186e-04 1.376250e-04
## Publicidad 7.774101e-04 8.523526e-04 9.344298e-04 1.024303e-03
## Poblacion 6.518306e-06 7.141236e-06 7.822373e-06 8.566882e-06
## Precio -3.622668e-04 -3.973760e-04 -4.358655e-04 -4.780562e-04
## CalidadEstantMalo -1.772207e-02 -1.943942e-02 -2.132208e-02 -2.338573e-02
## CalidadEstantMedio -2.913189e-03 -3.200923e-03 -3.517454e-03 -3.865738e-03
## Edad -2.758605e-04 -3.025973e-04 -3.319084e-04 -3.640383e-04
## Educacion -3.793059e-04 -4.157614e-04 -4.556653e-04 -4.993324e-04
## Urbano -6.420775e-04 -7.033617e-04 -7.703553e-04 -8.435616e-04
## USA 7.065870e-03 7.744373e-03 8.486930e-03 9.299368e-03
##
## (Intercept) 7.553105e+00 7.558557e+00 7.564524e+00 7.571052e+00
## PrecioCompt 1.207735e-04 1.328897e-04 1.462551e-04 1.610048e-04
## Ingreso 1.508854e-04 1.654067e-04 1.813057e-04 1.987089e-04
## Publicidad 1.122690e-03 1.230373e-03 1.348198e-03 1.477085e-03
## Poblacion 9.380344e-06 1.026876e-05 1.123858e-05 1.229673e-05
## Precio -5.242987e-04 -5.749755e-04 -6.305042e-04 -6.913399e-04
## CalidadEstantMalo -2.564751e-02 -2.812612e-02 -3.084195e-02 -3.381724e-02
## CalidadEstantMedio -4.249048e-03 -4.671012e-03 -5.135649e-03 -5.647421e-03
## Edad -3.992540e-04 -4.378468e-04 -4.801345e-04 -5.264638e-04
## Educacion -5.471044e-04 -5.993511e-04 -6.564725e-04 -7.189005e-04
## Urbano -9.235228e-04 -1.010821e-03 -1.106081e-03 -1.209968e-03
## USA 1.018800e-02 1.115965e-02 1.222169e-02 1.338209e-02
##
## (Intercept) 7.578192e+00 7.585999e+00 7.594533e+00 7.603857e+00
## PrecioCompt 1.772897e-04 1.952784e-04 2.151593e-04 2.371437e-04
## Ingreso 2.177541e-04 2.385903e-04 2.613792e-04 2.862956e-04
## Publicidad 1.618026e-03 1.772098e-03 1.940459e-03 2.124361e-03
## Poblacion 1.345058e-05 1.470802e-05 1.607742e-05 1.756764e-05
## Precio -7.579787e-04 -8.309608e-04 -9.108742e-04 -9.983580e-04
## CalidadEstantMalo -3.707624e-02 -4.064532e-02 -4.455321e-02 -4.883111e-02
## CalidadEstantMedio -6.211284e-03 -6.832742e-03 -7.517921e-03 -8.273635e-03
## Edad -5.772121e-04 -6.327907e-04 -6.936467e-04 -7.602664e-04
## Educacion -7.871006e-04 -8.615739e-04 -9.428584e-04 -1.031531e-03
## Urbano -1.323196e-03 -1.446517e-03 -1.580732e-03 -1.726681e-03
## USA 1.464940e-02 1.603282e-02 1.754223e-02 1.918816e-02
##
## (Intercept) 7.614039e+00 7.625155e+00 7.637283e+00 7.650508e+00
## PrecioCompt 2.614681e-04 2.883982e-04 3.182319e-04 3.513045e-04
## Ingreso 3.135284e-04 3.432814e-04 3.757739e-04 4.112418e-04
## Publicidad 2.325149e-03 2.544268e-03 2.783264e-03 3.043791e-03
## Poblacion 1.918804e-05 2.094841e-05 2.285901e-05 2.493046e-05
## Precio -1.094107e-03 -1.198874e-03 -1.313476e-03 -1.438799e-03
## CalidadEstantMalo -5.351293e-02 -5.863545e-02 -6.423854e-02 -7.036539e-02
## CalidadEstantMedio -9.107477e-03 -1.002791e-02 -1.104438e-02 -1.216743e-02
## Edad -8.331776e-04 -9.129528e-04 -1.000213e-03 -1.095628e-03
## Educacion -1.128206e-03 -1.233542e-03 -1.348236e-03 -1.473025e-03
## Urbano -1.885245e-03 -2.057342e-03 -2.243920e-03 -2.445952e-03
## USA 2.098187e-02 2.293531e-02 2.506114e-02 2.737273e-02
##
## (Intercept) 7.664921e+00 7.680618e+00 7.697701e+00 7.716278e+00
## PrecioCompt 3.879929e-04 4.287215e-04 4.739681e-04 5.242712e-04
## Ingreso 4.499380e-04 4.921330e-04 5.381159e-04 5.881940e-04
## Publicidad 3.327612e-03 3.636602e-03 3.972744e-03 4.338135e-03
## Poblacion 2.717371e-05 2.959994e-05 3.222046e-05 3.504659e-05
## Precio -1.575799e-03 -1.725509e-03 -1.889045e-03 -2.067605e-03
## CalidadEstantMalo -7.706265e-02 -8.438074e-02 -9.237398e-02 -1.011008e-01
## CalidadEstantMedio -1.340885e-02 -1.478180e-02 -1.630103e-02 -1.798302e-02
## Edad -1.199924e-03 -1.313884e-03 -1.438348e-03 -1.574223e-03
## Educacion -1.608689e-03 -1.756045e-03 -1.915946e-03 -2.089278e-03
## Urbano -2.664421e-03 -2.900317e-03 -3.154612e-03 -3.428245e-03
## USA 2.988411e-02 3.260995e-02 3.556548e-02 3.876643e-02
##
## (Intercept) 7.736462e+00 7.758372e+00 7.782131e+00 7.807867e+00
## PrecioCompt 5.802380e-04 6.425529e-04 7.119871e-04 7.894104e-04
## Ingreso 6.426937e-04 7.019599e-04 7.663561e-04 8.362634e-04
## Publicidad 4.734977e-03 5.165576e-03 5.632334e-03 6.137742e-03
## Poblacion 3.808947e-05 4.135988e-05 4.486801e-05 4.862319e-05
## Precio -2.262479e-03 -2.475050e-03 -2.706799e-03 -2.959305e-03
## CalidadEstantMalo -1.106242e-01 -1.210113e-01 -1.323343e-01 -1.446700e-01
## CalidadEstantMedio -1.984626e-02 -2.191142e-02 -2.420169e-02 -2.674302e-02
## Edad -1.722479e-03 -1.884153e-03 -2.060352e-03 -2.252253e-03
## Educacion -2.276958e-03 -2.479919e-03 -2.699113e-03 -2.935494e-03
## Urbano -3.722099e-03 -4.036968e-03 -4.373527e-03 -4.732291e-03
## USA 4.222888e-02 4.596917e-02 5.000366e-02 5.434858e-02
##
## (Intercept) 7.8357116809 7.865798e+00 7.898262e+00 7.9332365718
## PrecioCompt 0.0008758018 9.722637e-04 1.080035e-03 0.0012005081
## Ingreso 0.0009120799 9.942188e-04 1.083107e-03 0.0011791812
## Publicidad 0.0066843599 7.274810e-03 7.911751e-03 0.0085978577
## Poblacion 0.0000526336 5.690588e-05 6.144482e-05 0.0000662529
## Precio -0.0032342511 -3.533425e-03 -3.858720e-03 -0.0042121333
## CalidadEstantMalo -0.1581004478 -1.727125e-01 -1.885981e-01 -0.2058543399
## CalidadEstantMedio -0.0295644872 -3.269862e-02 -3.618183e-02 -0.0400547641
## Edad -0.0024611021 -2.688216e-03 -2.934977e-03 -0.0032028317
## Educacion -0.0031900082 -3.463579e-03 -3.757093e-03 -0.0040713788
## Urbano -0.0051135647 -5.517391e-03 -5.943490e-03 -0.0063911865
## USA 0.0590197108 6.403209e-02 6.939969e-02 0.0751349463
##
## (Intercept) 7.970856e+00 8.011247e+00 8.054532625 8.100824e+00
## PrecioCompt 1.335241e-03 1.485978e-03 0.001654664 1.843463e-03
## Ingreso 1.282887e-03 1.394674e-03 0.001514989 1.644275e-03
## Publicidad 9.335793e-03 1.012818e-02 0.010977560 1.188637e-02
## Poblacion 7.132985e-05 7.667224e-05 0.000082273 8.812097e-05
## Precio -4.595765e-03 -5.011815e-03 -0.005462577 -5.950432e-03
## CalidadEstantMalo -2.245833e-01 -2.448918e-01 -0.266891131 -2.906970e-01
## CalidadEstantMedio -4.436281e-02 -4.915653e-02 -0.054492118 -6.043193e-02
## Edad -3.493282e-03 -3.807880e-03 -0.004148219 -4.515915e-03
## Educacion -4.407186e-03 -4.765164e-03 -0.005145832 -5.549555e-03
## Urbano -6.859335e-03 -7.346234e-03 -0.007849539 -8.366162e-03
## USA 8.124834e-02 8.774788e-02 0.094638498 1.019215e-01
##
## (Intercept) 8.150220e+00 8.2028030720 8.2586390266 8.3177664043
## PrecioCompt 2.054773e-03 0.0022912595 0.0025558033 0.0028516005
## Ingreso 1.782962e-03 0.0019314606 0.0020901579 0.0022594040
## Publicidad 1.285687e-02 0.0138911595 0.0149910674 0.0161581526
## Poblacion 9.420053e-05 0.0001004911 0.0001069675 0.0001135988
## Precio -6.477840e-03 -0.0070473216 -0.0076614530 -0.0083228396
## CalidadEstantMalo -3.164286e-01 -0.3442084708 -0.3741617657 -0.4064151422
## CalidadEstantMedio -6.704493e-02 -0.0744071130 -0.0826019566 -0.0917207214
## Edad -4.912595e-03 -0.0053398791 -0.0057993513 -0.0062925376
## Educacion -5.976515e-03 -0.0064266805 -0.0068997760 -0.0073952583
## Urbano -8.892177e-03 -0.0094227259 -0.0099519043 -0.0104727013
## USA 1.095939e-01 0.1176476391 0.1260692605 0.1348388804
##
## (Intercept) 8.3801972407 8.4459118279 8.5148547791 8.586931353
## PrecioCompt 0.0031821124 0.0035510792 0.0039625137 0.004420687
## Ingreso 0.0024395069 0.0026307231 0.0028332480 0.003047207
## Publicidad 0.0173936481 0.0186984254 0.0200729614 0.021517312
## Poblacion 0.0001203492 0.0001271779 0.0001340396 0.000140885
## Precio -0.0090340996 -0.0097978386 -0.0106166228 -0.011492948
## CalidadEstantMalo -0.4410960784 -0.4783317242 -0.5182476851 -0.560966670
## CalidadEstantMedio -0.1018626915 -0.1131352736 -0.1256539260 -0.139541879
## Edad -0.0068208739 -0.0073856719 -0.0079880818 -0.008629052
## Educacion -0.0079122888 -0.0084497127 -0.0090060432 -0.009579452
## Urbano -0.0109769088 -0.0114550708 -0.0118964526 -0.012289044
## USA 0.1439297804 0.1533078211 0.1629309924 0.172749087
##
## (Intercept) 8.6620042049 8.739890751 8.8203613374 8.9031384086
## PrecioCompt 0.0049301042 0.005495471 0.0061216466 0.0068135829
## Ingreso 0.0032726491 0.003509534 0.0037577306 0.0040170076
## Publicidad 0.0230310950 0.024613479 0.0262631886 0.0279785129
## Poblacion 0.0001476619 0.000154316 0.0001607928 0.0001670383
## Precio -0.0124292053 -0.013427646 -0.0144903386 -0.0156191282
## CalidadEstantMalo -0.6066070021 -0.655281005 -0.7070932529 -0.7621387127
## CalidadEstantMedio -0.1549296051 -0.171953999 -0.1907572294 -0.2114852300
## Edad -0.0093092872 -0.010029205 -0.0107888929 -0.0115880685
## Educacion -0.0101677690 -0.010768488 -0.0113787889 -0.0119955616
## Urbano -0.0126195983 -0.012873720 -0.0130359974 -0.0130901944
## USA 0.1827035285 0.192727383 0.2027455769 0.2126753407
##
## (Intercept) 8.9878968458 9.0742656377 9.1618309924 9.2501409573
## PrecioCompt 0.0075762535 0.0084145661 0.0093332634 0.0103368117
## Ingreso 0.0042870316 0.0045673637 0.0048574597 0.0051566725
## Publicidad 0.0297573313 0.0315971447 0.0334951164 0.0354481195
## Poblacion 0.0001730015 0.0001786356 0.0001838996 0.0001887601
## Precio -0.0168155897 -0.0180809809 -0.0194161931 -0.0208217016
## CalidadEstantMalo -0.8205007638 -0.8822491228 -0.9474376766 -1.0161022439
## CalidadEstantMedio -0.2342858084 -0.2593063575 -0.2866911746 -0.3165784079
## Edad -0.0124260414 -0.0133016821 -0.0142133984 -0.0151591208
## Educacion -0.0126154499 -0.0132349002 -0.0138502207 -0.0144576502
## Urbano -0.0130194924 -0.0128067890 -0.0124350455 -0.0118876767
## USA 0.2224268969 0.2319043909 0.2410070640 0.2496306567
##
## (Intercept) 9.3387115455 9.4270342973 9.5145851268 9.6008342224
## PrecioCompt 0.0114292798 0.0126142107 0.0138944899 0.0152722140
## Ingreso 0.0054642560 0.0057793722 0.0061010996 0.0064284441
## Publicidad 0.0374527867 0.0395055612 0.0416027450 0.0437405414
## Poblacion 0.0001931925 0.0001971819 0.0002007237 0.0002038235
## Precio -0.0222975156 -0.0238431299 -0.0254574787 -0.0271388939
## CalidadEstantMalo -1.0882582905 -1.1638986283 -1.2429911439 -1.3254766122
## CalidadEstantMedio -0.3490966724 -0.3843613959 -0.4224709835 -0.4635029070
## Edad -0.0161363000 -0.0171419164 -0.0181725036 -0.0192241860
## Educacion -0.0150534313 -0.0156338873 -0.0161955013 -0.0167349910
## Urbano -0.0111489723 -0.0102045366 -0.0090417298 -0.0076500935
## USA 0.2576690157 0.2650158776 0.2715667861 0.2772210988
##
## (Intercept) 9.6851963735 9.7672611876 9.8465023120 9.9224742713
## PrecioCompt 0.0167491571 0.0183245168 0.0199977496 0.0217666876
## Ingreso 0.0067603712 0.0070957482 0.0074334550 0.0077723401
## Publicidad 0.0459147206 0.0481220010 0.0503581833 0.0526193155
## Poblacion 0.0002065025 0.0002087775 0.0002106845 0.0002122622
## Precio -0.0288851893 -0.0306932073 -0.0325593749 -0.0344793487
## CalidadEstantMalo -1.4112722868 -1.5002509856 -1.5922648474 -1.6871293360
## CalidadEstantMedio -0.5075112210 -0.5545183633 -0.6045177526 -0.6574675323
## Edad -0.0202927131 -0.0213735821 -0.0224620315 -0.0235531724
## Educacion -0.0172493442 -0.0177360161 -0.0181927945 -0.0186179571
## Urbano -0.0060221608 -0.0041522198 -0.0020387964 0.0003165434
## USA 0.2818855467 0.2854707625 0.2879007484 0.2891100805
##
## (Intercept) 9.9947787748 10.0630730945 10.1270767716 10.1865763691
## PrecioCompt 0.0236279067 0.0255767064 0.0276071227 0.0297119778
## Ingreso 0.0081112482 0.0084490350 0.0087845798 0.0091167980
## Publicidad 0.0549014116 0.0572004324 0.0595122600 0.0618326681
## Poblacion 0.0002135534 0.0002146024 0.0002154538 0.0002161495
## Precio -0.0364481029 -0.0384599523 -0.0405085925 -0.0425871578
## CalidadEstantMalo -1.7846262002 -1.8845037068 -1.9864776376 -2.0902331282
## CalidadEstantMedio -0.7132892361 -0.7718664859 -0.8330446245 -0.8966313685
## Edad -0.0246420654 -0.0257238097 -0.0267936313 -0.0278469663
## Educacion -0.0190102712 -0.0193690056 -0.0196939279 -0.0199852879
## Urbano 0.0029087729 0.0057294073 0.0087666070 0.0120053779
## USA 0.2890466064 0.2876728350 0.2849670385 0.2809240247
##
## (Intercept) 10.2414280884 10.2915581772 10.3369611765 10.3776961624
## PrecioCompt 0.0318829650 0.0341107688 0.0363852169 0.0386954583
## Ingreso 0.0094446525 0.0097671626 0.0100834128 0.0103925599
## Publicidad 0.0641572931 0.0664816090 0.0688009106 0.0711103076
## Poblacion 0.0002167278 0.0002172218 0.0002176585 0.0002180584
## Precio -0.0446882953 -0.0468042565 -0.0489270023 -0.0510483207
## CalidadEstantMalo -2.1954273921 -2.3016933354 -2.4086440218 -2.5158778954
## CalidadEstantMedio -0.9623985316 -1.0300848186 -1.0993996394 -1.1700278431
## Edad -0.0288795367 -0.0298874152 -0.0308670785 -0.0318154469
## Educacion -0.0202437871 -0.0204705369 -0.0206670072 -0.0208349678
## Urbano 0.0154278604 0.0190136978 0.0227404678 0.0265841617
## USA 0.2755555448 0.2688903113 0.2609736119 0.2518665208
##
## (Intercept) 10.4138812396 10.4456866178 10.4733266560 10.4967780611
## PrecioCompt 0.0410301627 0.0433777322 0.0457265192 0.0480685281
## Ingreso 0.0106938378 0.0109865624 0.0112701344 0.0115441968
## Publicidad 0.0734047328 0.0756789654 0.0779276689 0.0801462938
## Poblacion 0.0002184354 0.0002187976 0.0002191476 0.0002195204
## Precio -0.0531599512 -0.0552537145 -0.0573216412 -0.0593572904
## CalidadEstantMalo -2.6229846251 -2.7295513879 -2.8351693800 -2.9395420834
## CalidadEstantMedio -1.2416352212 -1.3138745890 -1.3863922240 -1.4588791109
## Edad -0.0327299096 -0.0336083370 -0.0344490797 -0.0352508512
## Educacion -0.0209764251 -0.0210935573 -0.0211886499 -0.0212642429
## Urbano 0.0305196934 0.0345214177 0.0385636426 0.0426232983
## USA 0.2416447207 0.2303969664 0.2182232366 0.2052239100
##
## (Intercept) 10.5168306399 10.5335403245 10.5472125932 10.5581553567
## PrecioCompt 0.0503861712 0.0526718803 0.0549158043 0.0571089458
## Ingreso 0.0118080349 0.0120614432 0.0123041674 0.0125360362
## Publicidad 0.0823282390 0.0844686292 0.0865622942 0.0886043008
## Poblacion 0.0002198406 0.0002201339 0.0002203921 0.0002206067
## Precio -0.0613512791 -0.0632979749 -0.0651913701 -0.0670261585
## CalidadEstantMalo -3.0421029229 -3.1425770958 -3.2406329801 -3.3359709405
## CalidadEstantMedio -1.5309079711 -1.6021800571 -1.6723784418 -1.7412089729
## Edad -0.0360131077 -0.0367354385 -0.0374179003 -0.0380608875
## Educacion -0.0213223313 -0.0213653087 -0.0213953333 -0.0214144278
## Urbano 0.0466722863 0.0506891306 0.0546523490 0.0585423424
## USA 0.1915280179 0.1772507544 0.1625146393 0.1474419363
##
## (Intercept) 10.56667233 10.5730574895 10.5775906354 10.5805340156
## PrecioCompt 0.05924327 0.0613117631 0.0633085053 0.0652286528
## Ingreso 0.01275696 0.0129669141 0.0131659594 0.0133542111
## Publicidad 0.09059003 0.0925152718 0.0943762520 0.0961697263
## Poblacion 0.00022077 0.0002208758 0.0002209193 0.0002208981
## Precio -0.06879778 -0.0705024633 -0.0721372024 -0.0736997777
## CalidadEstantMalo -3.42832674 -3.5174739173 -3.6032251662 -3.6854326851
## CalidadEstantMedio -1.80840422 -1.8737264837 -1.9369698497 -1.9979612914
## Edad -0.03866509 -0.0392314458 -0.0397611059 -0.0402553856
## Educacion -0.02142446 -0.0214271041 -0.0214238768 -0.0214160920
## Urbano 0.06234160 0.0660348059 0.0696089514 0.0730532916
## USA 0.13215244 0.1167614786 0.1013781117 0.0861036986
##
## (Intercept) 10.5821299855 10.5825995889 10.5821419466 10.5809343217
## PrecioCompt 0.0670684386 0.0688251314 0.0704969783 0.0720831324
## Ingreso 0.0135318454 0.0136990905 0.0138562201 0.0140035461
## Publicidad 0.0978930010 0.0995439627 0.1011210884 0.1026234419
## Poblacion 0.0002208114 0.0002206606 0.0002204487 0.0002201801
## Precio -0.0751887138 -0.0766032424 -0.0779432507 -0.0792092224
## CalidadEstantMalo -3.7639876289 -3.8388187317 -3.9098902373 -3.9771992770
## CalidadEstantMedio -2.0565608900 -2.1126612513 -2.1661862318 -2.2170890991
## Edad -0.0407157300 -0.0411436777 -0.0415408299 -0.0419088224
## Educacion -0.0214048870 -0.0213912271 -0.0213759177 -0.0213596191
## Urbano 0.0763593191 0.0795206645 0.0825329645 0.0853937027
## USA 0.0710307232 0.0562419675 0.0418099981 0.0277969504
##
## (Intercept) 10.5791327270 10.5768729459 10.5742718499 10.5714289071
## PrecioCompt 0.0735835694 0.0749989974 0.0763307630 0.0775807581
## Ingreso 0.0141414129 0.0142701900 0.0143902664 0.0145020448
## Publicidad 0.1040506567 0.1054029067 0.1066808682 0.1078856740
## Poblacion 0.0002198604 0.0002194958 0.0002190933 0.0002186597
## Precio -0.0804021722 -0.0815235783 -0.0825753134 -0.0835595779
## CalidadEstantMalo -4.0407728382 -4.1006644622 -4.1569508023 -4.2097281556
## CalidadEstantMedio -2.2653502543 -2.3109746456 -2.3539889921 -2.3944389246
## Edad -0.0422493016 -0.0425639044 -0.0428542414 -0.0431218835
## Educacion -0.0213428621 -0.0213260641 -0.0213095451 -0.0212935426
## Urbano 0.0881020320 0.0906585848 0.0930652804 0.0953251338
## USA 0.0142545837 0.0012245686 -0.0112610317 -0.0231791283
##
## (Intercept) 10.5684277961 10.5657421854 10.5626038367 10.5594777545
## PrecioCompt 0.0787513282 0.0798384668 0.0808588223 0.0818087290
## Ingreso 0.0146059360 0.0147020299 0.0147913988 0.0148741215
## Publicidad 0.1090188629 0.1100726602 0.1110685497 0.1119995477
## Poblacion 0.0002182022 0.0002177199 0.0002172375 0.0002167489
## Precio -0.0844788348 -0.0853330298 -0.0861304920 -0.0868713583
## CalidadEstantMalo -4.2591090667 -4.3049580515 -4.3479389818 -4.3879301387
## CalidadEstantMedio -2.4323861361 -2.4677608873 -2.5009409724 -2.5318747269
## Edad -0.0433683508 -0.0435953393 -0.0438037721 -0.0439952156
## Educacion -0.0212782259 -0.0212619424 -0.0212482836 -0.0212355679
## Urbano 0.0974420715 0.0994116274 0.1012574617 0.1029760907
## USA -0.0345148630 -0.0451654906 -0.0553201587 -0.0648910487ridge.mod$lambda## [1] 1255.0203235 1143.5277770 1041.9399211 949.3768503 865.0368276
## [6] 788.1893400 718.1687715 654.3686372 596.2363311 543.2683388
## [11] 495.0058769 451.0309191 410.9625754 374.4537929 341.1883500
## [16] 310.8781174 283.2605623 258.0964746 235.1678952 214.2762275
## [21] 195.2405181 177.8958886 162.0921081 147.6922920 134.5717159
## [26] 122.6167355 111.7238027 101.7985680 92.7550638 84.5149596
## [31] 77.0068835 70.1658042 63.9324676 58.2528834 53.0778578
## [36] 48.3625672 44.0661700 40.1514529 36.5845085 33.3344416
## [41] 30.3731017 27.6748390 25.2162826 22.9761376 20.9350008
## [46] 19.0751931 17.3806055 15.8365604 14.4296840 13.1477907
## [51] 11.9797772 10.9155268 9.9458215 9.0622621 8.2571957
## [56] 7.5236492 6.8552690 6.2462658 5.6913647 5.1857596
## [61] 4.7250710 4.3053087 3.9228369 3.5743429 3.2568081
## [66] 2.9674823 2.7038593 2.4636559 2.2447915 2.0453704
## [71] 1.8636654 1.6981025 1.5472477 1.4097945 1.2845522
## [76] 1.1704362 1.0664578 0.9717167 0.8853920 0.8067362
## [81] 0.7350680 0.6697666 0.6102664 0.5560520 0.5066539
## [86] 0.4616441 0.4206329 0.3832651 0.3492169 0.3181934
## [91] 0.2899260 0.2641698 0.2407016 0.2193184 0.1998347
## [96] 0.1820820 0.1659063 0.1511676 0.1377383 0.1255020plot(ridge.mod,"lambda", label=TRUE)
ridge.mod$lambda[5]## [1] 865.0368log(ridge.mod$lambda[5])## [1] 6.762772coef(ridge.mod)[,5] # Lambda más grande penaliza más tienden a ser los beta más pequeños## (Intercept) PrecioCompt Ingreso Publicidad
## 7.515093e+00 3.883450e-05 4.980280e-05 3.713377e-04
## Poblacion Precio CalidadEstantMalo CalidadEstantMedio
## 3.126349e-06 -1.726010e-04 -8.444076e-03 -1.375298e-03
## Edad Educacion Urbano USA
## -1.314284e-04 -1.814369e-04 -3.081310e-04 3.381306e-03plot(ridge.mod,"lambda", label=TRUE)
abline(v = log(ridge.mod$lambda[5]), col="blue", lwd=4, lty=3)
log(ridge.mod$lambda[70])## [1] 0.7155789coef(ridge.mod)[,70] # Lambda más grande penaliza más tienden a ser los beta más pequeños## (Intercept) PrecioCompt Ingreso Publicidad
## 10.0630730945 0.0255767064 0.0084490350 0.0572004324
## Poblacion Precio CalidadEstantMalo CalidadEstantMedio
## 0.0002146024 -0.0384599523 -1.8845037068 -0.7718664859
## Edad Educacion Urbano USA
## -0.0257238097 -0.0193690056 0.0057294073 0.2876728350plot(ridge.mod,"lambda", label=TRUE)
abline(v = log(ridge.mod$lambda[70]), col="blue", lwd=4, lty=3)
datosx<-model.matrix(Ventas~.,datos)[,-c(1,2)]
pred<-predict(ridge.mod,s=ridge.mod$lambda[5],newx=datosx)
# Medición de precisión
numero.predictoras <- dim(datosx)[2]-1
pre.ridge <- indices.precision(datos$Ventas,pred,numero.predictoras)
pre.ridge## $error.cuadratico
## [1] 7.927364
##
## $raiz.error.cuadratico
## [1] 2.855089
##
## $error.relativo
## [1] 0.3012258
##
## $correlacion
## [1] 0.7610886pred<-predict(ridge.mod,s=ridge.mod$lambda[70],newx=datosx)
# Medición de precisión
numero.predictoras <- dim(datosx)[2]-1
pre.ridge <- indices.precision(datos$Ventas,pred,numero.predictoras)
pre.ridge## $error.cuadratico
## [1] 3.453121
##
## $raiz.error.cuadratico
## [1] 1.884348
##
## $error.relativo
## [1] 0.1981819
##
## $correlacion
## [1] 0.8924282# Usando validación cruzada para determinar el mejor Lambda
sal.cv<-cv.glmnet(x,y,alpha=0)
plot(sal.cv)
mejor.lambda<-sal.cv$lambda.min
mejor.lambda## [1] 0.125502log(mejor.lambda)## [1] -2.075433coef(ridge.mod)[,which(ridge.mod$lambda==mejor.lambda)]## (Intercept) PrecioCompt Ingreso Publicidad
## 10.5594777545 0.0818087290 0.0148741215 0.1119995477
## Poblacion Precio CalidadEstantMalo CalidadEstantMedio
## 0.0002167489 -0.0868713583 -4.3879301387 -2.5318747269
## Edad Educacion Urbano USA
## -0.0439952156 -0.0212355679 0.1029760907 -0.0648910487plot(ridge.mod,"lambda", label=TRUE)
abline(v = log(mejor.lambda), col="blue", lwd=4, lty=3)
pred<-predict(ridge.mod,s=mejor.lambda,newx=datosx)
# Medición de precisión
numero.predictoras <- dim(datosx)[2]-1
pre.ridge <- indices.precision(datos$Ventas,pred,numero.predictoras)
pre.ridge## $error.cuadratico
## [1] 1.065489
##
## $raiz.error.cuadratico
## [1] 1.046718
##
## $error.relativo
## [1] 0.1096337
##
## $correlacion
## [1] 0.9340148###LASSO
# Debemos eliminar la columna 1
x<-model.matrix(Ventas~.,datos)[,-c(1,2)]
head(x)## PrecioCompt Ingreso Publicidad Poblacion Precio CalidadEstantMalo
## 1 138 73 11 276 120 1
## 2 111 48 16 260 83 0
## 3 113 35 10 269 80 0
## 4 117 100 4 466 97 0
## 5 141 64 3 340 128 1
## 6 124 113 13 501 72 1
## CalidadEstantMedio Edad Educacion Urbano USA
## 1 0 42 17 1 1
## 2 0 65 10 1 1
## 3 1 59 12 1 1
## 4 1 55 14 1 1
## 5 0 38 13 1 0
## 6 0 78 16 0 1# La siguiente instrucción construye la variable a predecir
y<-datos$Ventaslibrary(glmnet)
lasso.mod<-glmnet(x,y,alpha=1)
dim(coef(lasso.mod))## [1] 12 63coef(lasso.mod)## 12 x 63 sparse Matrix of class "dgCMatrix"## [[ suppressing 63 column names 's0', 's1', 's2' ... ]]##
## (Intercept) 7.496325 8.042282293 8.595065622 9.11933418 9.59702816
## PrecioCompt . . . . .
## Ingreso . . . . .
## Publicidad . . . . .
## Poblacion . . . . .
## Precio . -0.004714861 -0.009125493 -0.01318696 -0.01688762
## CalidadEstantMalo . . -0.175225562 -0.40010391 -0.60500469
## CalidadEstantMedio . . . . .
## Edad . . . . .
## Educacion . . . . .
## Urbano . . . . .
## USA . . . . .
##
## (Intercept) 10.03228512 10.4259716101 11.020131312 11.561507854
## PrecioCompt . . . .
## Ingreso . . . .
## Publicidad . 0.0078665024 0.017577019 0.026424902
## Poblacion . . . .
## Precio -0.02025952 -0.0234725436 -0.026716715 -0.029672687
## CalidadEstantMalo -0.79170265 -0.9588454343 -1.117097739 -1.261291390
## CalidadEstantMedio . . . .
## Edad . -0.0006322802 -0.005226018 -0.009411661
## Educacion . . . .
## Urbano . . . .
## USA . . . .
##
## (Intercept) 11.704683428 11.69977844 11.69549696 11.6622772936
## PrecioCompt 0.004810848 0.01243838 0.01938676 0.0257472917
## Ingreso . . . 0.0003609279
## Publicidad 0.034849758 0.04240721 0.04929242 0.0554701330
## Poblacion . . . .
## Precio -0.034218275 -0.03967847 -0.04465313 -0.0491725061
## CalidadEstantMalo -1.442750566 -1.73813979 -2.00735887 -2.2543339108
## CalidadEstantMedio -0.073816801 -0.32413307 -0.55224940 -0.7599784361
## Edad -0.012974679 -0.01594313 -0.01864796 -0.0211071527
## Educacion . . . .
## Urbano . . . .
## USA . . . .
##
## (Intercept) 11.54175589 11.432409927 11.332778164 11.241997411
## PrecioCompt 0.03168634 0.037095205 0.042023563 0.046514100
## Ingreso 0.00173055 0.002979105 0.004116743 0.005153316
## Publicidad 0.06084223 0.065733716 0.070190652 0.074251647
## Poblacion . . . .
## Precio -0.05327244 -0.057007731 -0.060411194 -0.063512303
## CalidadEstantMalo -2.48327718 -2.692257203 -2.882672510 -3.056171846
## CalidadEstantMedio -0.94844387 -1.120364842 -1.277013085 -1.419745131
## Edad -0.02332962 -0.025354919 -0.027200300 -0.028881742
## Educacion . . . .
## Urbano . . . .
## USA . . . .
##
## (Intercept) 11.159281371 11.083913595 11.015241285 10.952669634
## PrecioCompt 0.050605709 0.054333831 0.057730757 0.060825910
## Ingreso 0.006097803 0.006958384 0.007742514 0.008456983
## Publicidad 0.077951875 0.081323384 0.084395378 0.087194464
## Poblacion . . . .
## Precio -0.066337918 -0.068912513 -0.071258388 -0.073395862
## CalidadEstantMalo -3.214257979 -3.358300176 -3.489546061 -3.609132423
## CalidadEstantMedio -1.549797256 -1.668295908 -1.776267466 -1.874647129
## Edad -0.030413810 -0.031809772 -0.033081722 -0.034240675
## Educacion . . . .
## Urbano . . . .
## USA . . . .
##
## (Intercept) 10.895656676 10.844523277 10.79712287 10.75392829
## PrecioCompt 0.063646098 0.066203783 0.06854615 0.07068049
## Ingreso 0.009107982 0.009700824 0.01024132 0.01073380
## Publicidad 0.089744887 0.092068154 0.09418560 0.09611495
## Poblacion . . . .
## Precio -0.075343449 -0.077113100 -0.07873043 -0.08020411
## CalidadEstantMalo -3.718095063 -3.817091853 -3.90757916 -3.99002862
## CalidadEstantMedio -1.964287014 -2.045804297 -2.12023859 -2.18806081
## Edad -0.035296669 -0.036259201 -0.03713588 -0.03793467
## Educacion . . . .
## Urbano . . . .
## USA . . . .
##
## (Intercept) 10.71457096 10.67871004 10.64603489 10.61626252 10.58913504
## PrecioCompt 0.07262522 0.07439719 0.07601175 0.07748287 0.07882330
## Ingreso 0.01118254 0.01159140 0.01196395 0.01230340 0.01261269
## Publicidad 0.09787290 0.09947468 0.10093417 0.10226399 0.10347568
## Poblacion . . . . .
## Precio -0.08154687 -0.08277034 -0.08388513 -0.08490088 -0.08582639
## CalidadEstantMalo -4.06515349 -4.13360447 -4.19597446 -4.25280367 -4.30458433
## CalidadEstantMedio -2.24985789 -2.30616508 -2.35747010 -2.40421732 -2.44681165
## Edad -0.03866250 -0.03932567 -0.03992993 -0.04048051 -0.04098217
## Educacion . . . . .
## Urbano . . . . .
## USA . . . . .
##
## (Intercept) 10.56441750 10.54189579 10.52137485 10.527800397
## PrecioCompt 0.08004465 0.08115749 0.08217148 0.083100135
## Ingreso 0.01289451 0.01315129 0.01338526 0.013589591
## Publicidad 0.10457972 0.10558569 0.10650229 0.107315333
## Poblacion . . . .
## Precio -0.08666968 -0.08743806 -0.08813818 -0.088775734
## CalidadEstantMalo -4.35176494 -4.39475415 -4.43392432 -4.469399500
## CalidadEstantMedio -2.48562202 -2.52098458 -2.55320562 -2.582359710
## Edad -0.04143927 -0.04185576 -0.04223525 -0.042578835
## Educacion . . . -0.001819095
## Urbano . . . .
## USA . . . .
##
## (Intercept) 10.534674429 10.536397694 10.539466796 1.053260e+01
## PrecioCompt 0.083940025 0.084710773 0.085381970 8.602881e-02
## Ingreso 0.013774392 0.013938763 0.014087180 1.422654e-02
## Publicidad 0.108058654 0.108710009 0.109295829 1.097175e-01
## Poblacion . . . 1.928014e-05
## Precio -0.089353292 -0.089891814 -0.090371874 -9.082042e-02
## CalidadEstantMalo -4.501114221 -4.531584233 -4.559073542 -4.584924e+00
## CalidadEstantMedio -2.608592702 -2.633046180 -2.655109707 -2.675443e+00
## Edad -0.042891792 -0.043186309 -0.043457369 -4.369634e-02
## Educacion -0.003539897 -0.005056452 -0.006428301 -7.569676e-03
## Urbano . 0.008779033 0.018366597 2.749760e-02
## USA . . . .
##
## (Intercept) 1.052362e+01 1.051529e+01 1.050770e+01 10.5007751572
## PrecioCompt 8.661940e-02 8.716091e-02 8.765438e-02 0.0881040153
## Ingreso 1.435459e-02 1.447137e-02 1.457779e-02 0.0146747446
## Publicidad 1.100650e-01 1.103812e-01 1.106693e-01 0.1109318534
## Poblacion 4.319623e-05 6.502944e-05 8.492402e-05 0.0001030512
## Precio -9.122781e-02 -9.160067e-02 -9.194043e-02 -0.0922500097
## CalidadEstantMalo -4.608134e+00 -4.629502e+00 -4.648972e+00 -4.6667135569
## CalidadEstantMedio -2.693720e+00 -2.710490e+00 -2.725771e+00 -2.7396945714
## Edad -4.391155e-02 -4.410761e-02 -4.428625e-02 -0.0444490126
## Educacion -8.575171e-03 -9.490611e-03 -1.032472e-02 -0.0110847248
## Urbano 3.592631e-02 4.361529e-02 5.062123e-02 0.0570047915
## USA . . . .
##
## (Intercept) 10.4951315886 10.4967381739 10.4979909469 10.4991293375
## PrecioCompt 0.0885137054 0.0888935427 0.0892420065 0.0895594561
## Ingreso 0.0147630903 0.0148569756 0.0149409987 0.0150175618
## Publicidad 0.1111710615 0.1122735951 0.1132365569 0.1141124228
## Poblacion 0.0001195681 0.0001270701 0.0001342338 0.0001407755
## Precio -0.0925320856 -0.0927816422 -0.0930105205 -0.0932190581
## CalidadEstantMalo -4.6828785828 -4.6976972800 -4.7112451073 -4.7235880182
## CalidadEstantMedio -2.7523811287 -2.7649378404 -2.7763585794 -2.7867623558
## Edad -0.0445973199 -0.0447256752 -0.0448428818 -0.0449496886
## Educacion -0.0117772148 -0.0126157061 -0.0133699702 -0.0140568624
## Urbano 0.0628212504 0.0681611118 0.0730227956 0.0774525407
## USA -0.0010277601 -0.0177122566 -0.0325083866 -0.0459753121
##
## (Intercept) 10.5001666357 10.5017566971 10.5025972098 10.5033284005
## PrecioCompt 0.0898487003 0.0901013109 0.0903418061 0.0905615133
## Ingreso 0.0150873234 0.0151507369 0.0152086714 0.0152614559
## Publicidad 0.1149104204 0.1156045967 0.1162676480 0.1168740042
## Poblacion 0.0001467366 0.0001523542 0.0001573036 0.0001617978
## Precio -0.0934090686 -0.0935780503 -0.0937359520 -0.0938800312
## CalidadEstantMalo -4.7348343448 -4.7448398753 -4.7541909209 -4.7627182614
## CalidadEstantMedio -2.7962417868 -2.8047119621 -2.8125901871 -2.8197747826
## Edad -0.0450470075 -0.0451362431 -0.0452170272 -0.0452905990
## Educacion -0.0146827192 -0.0152459760 -0.0157656482 -0.0162396598
## Urbano 0.0814887592 0.0851647309 0.0885161357 0.0915695199
## USA -0.0582453132 -0.0691066250 -0.0792989879 -0.0886069245
##
## (Intercept) 10.5039927776 10.5045980317 10.5051495108 10.5056519977
## PrecioCompt 0.0907617352 0.0909441718 0.0911104014 0.0912618636
## Ingreso 0.0153095507 0.0153533728 0.0153933019 0.0154296838
## Publicidad 0.1174266553 0.1179302224 0.1183890548 0.1188071258
## Poblacion 0.0001658914 0.0001696213 0.0001730199 0.0001761165
## Precio -0.0940113220 -0.0941309499 -0.0942399504 -0.0943392677
## CalidadEstantMalo -4.7704883443 -4.7775681709 -4.7840190464 -4.7898968440
## CalidadEstantMedio -2.8263214529 -2.8322865569 -2.8377217391 -2.8426740748
## Edad -0.0453576325 -0.0454187109 -0.0454743631 -0.0455250714
## Educacion -0.0166715993 -0.0170651694 -0.0174237759 -0.0177505249
## Urbano 0.0943516264 0.0968865768 0.0991963291 0.1013008894
## USA -0.0970895067 -0.1048186326 -0.1118611327 -0.1182779971
##
## (Intercept) 10.506109845 10.5073834588 10.507816930 10.5081004410
## PrecioCompt 0.091399870 0.0915119196 0.091625799 0.0917312149
## Ingreso 0.015462834 0.0154928221 0.015520368 0.0155454647
## Publicidad 0.119188057 0.1195029926 0.119817528 0.1201080339
## Poblacion 0.000178938 0.0001816507 0.000184006 0.0001861307
## Precio -0.094429762 -0.0945069321 -0.094581829 -0.0946506809
## CalidadEstantMalo -4.795252474 -4.7998404442 -4.804292859 -4.8083680572
## CalidadEstantMedio -2.847186459 -2.8511042389 -2.854851694 -2.8582806552
## Edad -0.045571275 -0.0456140129 -0.045652416 -0.0456873208
## Educacion -0.018048246 -0.0183129302 -0.018559655 -0.0187853401
## Urbano 0.103218486 0.1049643564 0.106557745 0.1080085853
## USA -0.124124805 -0.1291398925 -0.133978268 -0.1384240505
##
## (Intercept) 10.5083432064 10.5085623004 10.5087616483 10.5089432488
## PrecioCompt 0.0918274906 0.0919152439 0.0919952055 0.0920680641
## Ingreso 0.0155683294 0.0155891624 0.0156081446 0.0156254405
## Publicidad 0.1203732988 0.1206150810 0.1208353959 0.1210361405
## Poblacion 0.0001880633 0.0001898236 0.0001914274 0.0001928887
## Precio -0.0947134975 -0.0947707445 -0.0948229072 -0.0948704361
## CalidadEstantMalo -4.8120826128 -4.8154673041 -4.8185513230 -4.8213613680
## CalidadEstantMedio -2.8614064043 -2.8642546345 -2.8668498574 -2.8692145308
## Edad -0.0457191126 -0.0457480783 -0.0457744705 -0.0457985181
## Educacion -0.0189911085 -0.0191786166 -0.0193494699 -0.0195051455
## Urbano 0.1093303268 0.1105346159 0.1116319148 0.1126317320
## USA -0.1424802285 -0.1461768441 -0.1495451760 -0.1526142910
##
## (Intercept) 10.5101802475
## PrecioCompt 0.0921175783
## Ingreso 0.0156407178
## Publicidad 0.1211836561
## Poblacion 0.0001942996
## Precio -0.0949070828
## CalidadEstantMalo -4.8235162298
## CalidadEstantMedio -2.8711100334
## Edad -0.0458211287
## Educacion -0.0196404504
## Urbano 0.1135363121
## USA -0.1550627296lasso.mod$lambda## [1] 1.255020323 1.143527777 1.041939921 0.949376850 0.865036828 0.788189340
## [7] 0.718168771 0.654368637 0.596236331 0.543268339 0.495005877 0.451030919
## [13] 0.410962575 0.374453793 0.341188350 0.310878117 0.283260562 0.258096475
## [19] 0.235167895 0.214276228 0.195240518 0.177895889 0.162092108 0.147692292
## [25] 0.134571716 0.122616736 0.111723803 0.101798568 0.092755064 0.084514960
## [31] 0.077006884 0.070165804 0.063932468 0.058252883 0.053077858 0.048362567
## [37] 0.044066170 0.040151453 0.036584508 0.033334442 0.030373102 0.027674839
## [43] 0.025216283 0.022976138 0.020935001 0.019075193 0.017380605 0.015836560
## [49] 0.014429684 0.013147791 0.011979777 0.010915527 0.009945821 0.009062262
## [55] 0.008257196 0.007523649 0.006855269 0.006246266 0.005691365 0.005185760
## [61] 0.004725071 0.004305309 0.003922837plot(lasso.mod,"lambda", label=TRUE)
lasso.mod$lambda[5]## [1] 0.8650368log(lasso.mod$lambda[5])## [1] -0.1449832coef(lasso.mod)[,5] # Lambda más grande penaliza más tienden a ser los beta más pequeños## (Intercept) PrecioCompt Ingreso Publicidad
## 9.59702816 0.00000000 0.00000000 0.00000000
## Poblacion Precio CalidadEstantMalo CalidadEstantMedio
## 0.00000000 -0.01688762 -0.60500469 0.00000000
## Edad Educacion Urbano USA
## 0.00000000 0.00000000 0.00000000 0.00000000plot(lasso.mod,"lambda", label=TRUE)
abline(v = log(lasso.mod$lambda[5]), col="blue", lwd=4, lty=3)
lasso.mod$lambda[60]## [1] 0.00518576log(lasso.mod$lambda[60])## [1] -5.261839coef(lasso.mod)[,60] # Lambda más grande penaliza más tienden a ser los beta más pequeños## (Intercept) PrecioCompt Ingreso Publicidad
## 10.5085623004 0.0919152439 0.0155891624 0.1206150810
## Poblacion Precio CalidadEstantMalo CalidadEstantMedio
## 0.0001898236 -0.0947707445 -4.8154673041 -2.8642546345
## Edad Educacion Urbano USA
## -0.0457480783 -0.0191786166 0.1105346159 -0.1461768441plot(lasso.mod,"lambda", label=TRUE)
abline(v = log(lasso.mod$lambda[60]), col="blue", lwd=4, lty=3)
datosx<-model.matrix(Ventas~.,datos)[,-c(1,2)]
pred<-predict(lasso.mod,s=lasso.mod$lambda[5],newx=datosx)
# Medición de precisión
numero.predictoras <- dim(datosx)[2]-1
pre.lasso <- indices.precision(datos$Ventas,pred,numero.predictoras)
pre.lasso## $error.cuadratico
## [1] 6.599002
##
## $raiz.error.cuadratico
## [1] 2.60492
##
## $error.relativo
## [1] 0.2751099
##
## $correlacion
## [1] 0.5971009pred<-predict(lasso.mod,s=lasso.mod$lambda[60],newx=datosx)
# Medición de precisión
numero.predictoras <- dim(datosx)[2]-1
pre.lasso <- indices.precision(datos$Ventas,pred,numero.predictoras)
pre.lasso## $error.cuadratico
## [1] 1.007691
##
## $raiz.error.cuadratico
## [1] 1.017932
##
## $error.relativo
## [1] 0.1071899
##
## $correlacion
## [1] 0.9345484El error en este caso se mide entre otros por la raiz del error cuadratico medio. Ya que lo que indica este coeficiente es que la estimacion del modelo tiene un error absoluto estimado de + (mas) o (-) 1180 unidades de asientos vendidos en el caso de regresion multiple, contra + (mas) o (-) 1047 unidades de asientos vendidos en el caso de regresion Ridge, y + (mas) o (-) 1018 unidades de asientos vendidos en el caso de regresion Lasso. El error relativo indica que el error de estimacion es aproximado de 11,46% y ademas la correlacion entre el valor real y el valor predicho es 0.9283687 en la regresion multiple. Por su parte en Ridge, el error relativo indica que el error de estimacion es aproximado de 10,96% y ademas la correlacion entre el valor real y el valor predicho es 0.9340148 en la regresion multiple.Finalmente, en Lasso, el error relativo indica que el error de estimacion es aproximado de 10,72% y ademas la correlacion entre el valor real y el valor predicho es 0.9345484 en la regresion multiple.Curiosamente esto indica que el mejor ajuste se encuentra en la regresion de Lasso, para el caso de training, cabe indicar que las diferencias no resultan significativas, por lo que puede estar asociado a la seleccion de training vs test.
- ¿En regresi´on Lasso, qu´e valor de λ tomar´ıa si se le pidiera obtener un modelo que no le de tanta importancia al error de predicci´on pero que sea mucho m´as f´acil de interpretar (es decir que a´un m´as coeficientes de la regresi´on sean nulos)? Genere dicho modelo, muestre los coeficientes y las medidas de error.
# Validación Cruzada
sal.cv<-cv.glmnet(x,y,alpha=1)
plot(sal.cv)
mejor.lambda<-sal.cv$lambda.min
mejor.lambda## [1] 0.003922837log(mejor.lambda)## [1] -5.54094coef(lasso.mod)[,which(lasso.mod$lambda==mejor.lambda)]## (Intercept) PrecioCompt Ingreso Publicidad
## 10.5101802475 0.0921175783 0.0156407178 0.1211836561
## Poblacion Precio CalidadEstantMalo CalidadEstantMedio
## 0.0001942996 -0.0949070828 -4.8235162298 -2.8711100334
## Edad Educacion Urbano USA
## -0.0458211287 -0.0196404504 0.1135363121 -0.1550627296plot(lasso.mod,"lambda", label=TRUE)
abline(v = log(mejor.lambda), col="blue", lwd=4, lty=3)
pred<-predict(lasso.mod,s=mejor.lambda,newx=datosx)
# Medición de precisión
numero.predictoras<- dim(datosx)[2]-1
numero.predictoras## [1] 10pre.lasso <- indices.precision(datos$Ventas,pred,numero.predictoras)
pre.lasso## $error.cuadratico
## [1] 1.00744
##
## $raiz.error.cuadratico
## [1] 1.017806
##
## $error.relativo
## [1] 0.1071834
##
## $correlacion
## [1] 0.9345557El mejor lambda es de 0.003922837 y se genera en la grafica (mejor.lambda) en -5.54094.
Pregunta 3: La Tabla de Datos uscrime.csv contiene el c´alculo de´ındice de cr´ımenes violentos por habitante en Estados Unidos, como son el asesinato, la violaci´on, el robo y asalto. Las variables incluidas son, entre otras, el porcentaje de la poblaci´on considerada urbana, la renta media de la familia, la participaci´on de las fuerzas del orden, el n´umero de polic´ıas per c´apita, el porcentaje de los oficiales asignados a las unidades de la droga. La variable a predecir es ViolentCrimesPerPop (Per Capita Violent Crimes in US). Usando un 67 % de esta tabla para Tabla de Aprendizaje y el restante 33 % para Tabla de Testing efectue lo siguiente:
- Construya un modelo predictivo para la variable ViolentCrimesPerPop usando una Regresi´on Lineal M´ultiple con la funci´on lm(…) en la Tabla de Aprendizaje y calcule Error Est´andar de los Residuos para este modelo, adem´as calcule el Error Cuadr´atico Medio y el Error Relativo para la Tabla de Testing.
setwd("C:/Users/rzamoram/Documents/Machine Learning/Mineria de Datos I/Clase8")
datos<-read.csv("uscrime.csv",dec='.',header=T)
str(datos)## 'data.frame': 1994 obs. of 103 variables:
## $ state : int 8 53 24 34 42 6 44 6 21 29 ...
## $ fold : int 1 1 1 1 1 1 1 1 1 1 ...
## $ population : num 0.19 0 0 0.04 0.01 0.02 0.01 0.01 0.03 0.01 ...
## $ householdsize : num 0.33 0.16 0.42 0.77 0.55 0.28 0.39 0.74 0.34 0.4 ...
## $ racepctblack : num 0.02 0.12 0.49 1 0.02 0.06 0 0.03 0.2 0.06 ...
## $ racePctWhite : num 0.9 0.74 0.56 0.08 0.95 0.54 0.98 0.46 0.84 0.87 ...
## $ racePctAsian : num 0.12 0.45 0.17 0.12 0.09 1 0.06 0.2 0.02 0.3 ...
## $ racePctHisp : num 0.17 0.07 0.04 0.1 0.05 0.25 0.02 1 0 0.03 ...
## $ agePct12t21 : num 0.34 0.26 0.39 0.51 0.38 0.31 0.3 0.52 0.38 0.9 ...
## $ agePct12t29 : num 0.47 0.59 0.47 0.5 0.38 0.48 0.37 0.55 0.45 0.82 ...
## $ agePct16t24 : num 0.29 0.35 0.28 0.34 0.23 0.27 0.23 0.36 0.28 0.8 ...
## $ agePct65up : num 0.32 0.27 0.32 0.21 0.36 0.37 0.6 0.35 0.48 0.39 ...
## $ numbUrban : num 0.2 0.02 0 0.06 0.02 0.04 0.02 0 0.04 0.02 ...
## $ pctUrban : num 1 1 0 1 0.9 1 0.81 0 1 1 ...
## $ medIncome : num 0.37 0.31 0.3 0.58 0.5 0.52 0.42 0.16 0.17 0.54 ...
## $ pctWWage : num 0.72 0.72 0.58 0.89 0.72 0.68 0.5 0.44 0.47 0.59 ...
## $ pctWFarmSelf : num 0.34 0.11 0.19 0.21 0.16 0.2 0.23 1 0.36 0.22 ...
## $ pctWInvInc : num 0.6 0.45 0.39 0.43 0.68 0.61 0.68 0.23 0.34 0.86 ...
## $ pctWSocSec : num 0.29 0.25 0.38 0.36 0.44 0.28 0.61 0.53 0.55 0.42 ...
## $ pctWPubAsst : num 0.15 0.29 0.4 0.2 0.11 0.15 0.21 0.97 0.48 0.02 ...
## $ pctWRetire : num 0.43 0.39 0.84 0.82 0.71 0.25 0.54 0.41 0.43 0.31 ...
## $ medFamInc : num 0.39 0.29 0.28 0.51 0.46 0.62 0.43 0.15 0.21 0.85 ...
## $ perCapInc : num 0.4 0.37 0.27 0.36 0.43 0.72 0.47 0.1 0.23 0.89 ...
## $ whitePerCap : num 0.39 0.38 0.29 0.4 0.41 0.76 0.44 0.12 0.23 0.94 ...
## $ blackPerCap : num 0.32 0.33 0.27 0.39 0.28 0.77 0.4 0.08 0.19 0.11 ...
## $ indianPerCap : num 0.27 0.16 0.07 0.16 0 0.28 0.24 0.17 0.1 0.09 ...
## $ AsianPerCap : num 0.27 0.3 0.29 0.25 0.74 0.52 0.86 0.27 0.26 0.33 ...
## $ OtherPerCap : num 0.36 0.22 0.28 0.36 0.51 0.48 0.24 0.18 0.29 0.17 ...
## $ HispPerCap : num 0.41 0.35 0.39 0.44 0.48 0.6 0.36 0.21 0.22 0.8 ...
## $ NumUnderPov : num 0.08 0.01 0.01 0.01 0 0.01 0.01 0.03 0.04 0 ...
## $ PctPopUnderPov : num 0.19 0.24 0.27 0.1 0.06 0.12 0.11 0.64 0.45 0.11 ...
## $ PctLess9thGrade : num 0.1 0.14 0.27 0.09 0.25 0.13 0.29 0.96 0.52 0.04 ...
## $ PctNotHSGrad : num 0.18 0.24 0.43 0.25 0.3 0.12 0.41 0.82 0.59 0.03 ...
## $ PctBSorMore : num 0.48 0.3 0.19 0.31 0.33 0.8 0.36 0.12 0.17 1 ...
## $ PctUnemployed : num 0.27 0.27 0.36 0.33 0.12 0.1 0.28 1 0.55 0.11 ...
## $ PctEmploy : num 0.68 0.73 0.58 0.71 0.65 0.65 0.54 0.26 0.43 0.44 ...
## $ PctEmplManu : num 0.23 0.57 0.32 0.36 0.67 0.19 0.44 0.43 0.59 0.2 ...
## $ PctEmplProfServ : num 0.41 0.15 0.29 0.45 0.38 0.77 0.53 0.34 0.36 1 ...
## $ PctOccupManu : num 0.25 0.42 0.49 0.37 0.42 0.06 0.33 0.71 0.64 0.02 ...
## $ PctOccupMgmtProf : num 0.52 0.36 0.32 0.39 0.46 0.91 0.49 0.18 0.29 0.96 ...
## $ MalePctDivorce : num 0.68 1 0.63 0.34 0.22 0.49 0.25 0.38 0.62 0.3 ...
## $ MalePctNevMarr : num 0.4 0.63 0.41 0.45 0.27 0.57 0.34 0.47 0.26 0.85 ...
## $ FemalePctDiv : num 0.75 0.91 0.71 0.49 0.2 0.61 0.28 0.59 0.66 0.39 ...
## $ TotalPctDiv : num 0.75 1 0.7 0.44 0.21 0.58 0.28 0.52 0.67 0.36 ...
## $ PersPerFam : num 0.35 0.29 0.45 0.75 0.51 0.44 0.42 0.78 0.37 0.31 ...
## $ PctFam2Par : num 0.55 0.43 0.42 0.65 0.91 0.62 0.77 0.45 0.51 0.65 ...
## $ PctKids2Par : num 0.59 0.47 0.44 0.54 0.91 0.69 0.81 0.43 0.55 0.73 ...
## $ PctYoungKids2Par : num 0.61 0.6 0.43 0.83 0.89 0.87 0.79 0.34 0.58 0.78 ...
## $ PctTeen2Par : num 0.56 0.39 0.43 0.65 0.85 0.53 0.74 0.34 0.47 0.67 ...
## $ PctWorkMomYoungKids : num 0.74 0.46 0.71 0.85 0.4 0.3 0.57 0.29 0.65 0.72 ...
## $ PctWorkMom : num 0.76 0.53 0.67 0.86 0.6 0.43 0.62 0.27 0.64 0.71 ...
## $ NumIlleg : num 0.04 0 0.01 0.03 0 0 0 0.02 0.02 0 ...
## $ PctIlleg : num 0.14 0.24 0.46 0.33 0.06 0.11 0.13 0.5 0.29 0.07 ...
## $ NumImmig : num 0.03 0.01 0 0.02 0 0.04 0.01 0.02 0 0.01 ...
## $ PctImmigRecent : num 0.24 0.52 0.07 0.11 0.03 0.3 0 0.5 0.12 0.41 ...
## $ PctImmigRec5 : num 0.27 0.62 0.06 0.2 0.07 0.35 0.02 0.59 0.09 0.44 ...
## $ PctImmigRec8 : num 0.37 0.64 0.15 0.3 0.2 0.43 0.02 0.65 0.07 0.52 ...
## $ PctImmigRec10 : num 0.39 0.63 0.19 0.31 0.27 0.47 0.1 0.59 0.13 0.48 ...
## $ PctRecentImmig : num 0.07 0.25 0.02 0.05 0.01 0.5 0 0.69 0 0.22 ...
## $ PctRecImmig5 : num 0.07 0.27 0.02 0.08 0.02 0.5 0.01 0.72 0 0.21 ...
## $ PctRecImmig8 : num 0.08 0.25 0.04 0.11 0.04 0.56 0.01 0.71 0 0.22 ...
## $ PctRecImmig10 : num 0.08 0.23 0.05 0.11 0.05 0.57 0.03 0.6 0 0.19 ...
## $ PctSpeakEnglOnly : num 0.89 0.84 0.88 0.81 0.88 0.45 0.73 0.12 0.99 0.85 ...
## $ PctNotSpeakEnglWell : num 0.06 0.1 0.04 0.08 0.05 0.28 0.05 0.93 0.01 0.03 ...
## $ PctLargHouseFam : num 0.14 0.16 0.2 0.56 0.16 0.25 0.12 0.74 0.12 0.09 ...
## $ PctLargHouseOccup : num 0.13 0.1 0.2 0.62 0.19 0.19 0.13 0.75 0.12 0.06 ...
## $ PersPerOccupHous : num 0.33 0.17 0.46 0.85 0.59 0.29 0.42 0.8 0.35 0.15 ...
## $ PersPerOwnOccHous : num 0.39 0.29 0.52 0.77 0.6 0.53 0.54 0.68 0.38 0.34 ...
## $ PersPerRentOccHous : num 0.28 0.17 0.43 1 0.37 0.18 0.24 0.92 0.33 0.05 ...
## $ PctPersOwnOccup : num 0.55 0.26 0.42 0.94 0.89 0.39 0.65 0.39 0.5 0.48 ...
## $ PctPersDenseHous : num 0.09 0.2 0.15 0.12 0.02 0.26 0.03 0.89 0.1 0.03 ...
## $ PctHousLess3BR : num 0.51 0.82 0.51 0.01 0.19 0.73 0.46 0.66 0.64 0.58 ...
## $ MedNumBR : num 0.5 0 0.5 0.5 0.5 0 0.5 0 0 0 ...
## $ HousVacant : num 0.21 0.02 0.01 0.01 0.01 0.02 0.01 0.01 0.04 0.02 ...
## $ PctHousOccup : num 0.71 0.79 0.86 0.97 0.89 0.84 0.89 0.91 0.72 0.72 ...
## $ PctHousOwnOcc : num 0.52 0.24 0.41 0.96 0.87 0.3 0.57 0.46 0.49 0.38 ...
## $ PctVacantBoarded : num 0.05 0.02 0.29 0.6 0.04 0.16 0.09 0.22 0.05 0.07 ...
## $ PctVacMore6Mos : num 0.26 0.25 0.3 0.47 0.55 0.28 0.49 0.37 0.49 0.47 ...
## $ MedYrHousBuilt : num 0.65 0.65 0.52 0.52 0.73 0.25 0.38 0.6 0.5 0.04 ...
## $ PctHousNoPhone : num 0.14 0.16 0.47 0.11 0.05 0.02 0.05 0.28 0.57 0.01 ...
## $ PctWOFullPlumb : num 0.06 0 0.45 0.11 0.14 0.05 0.05 0.23 0.22 0 ...
## $ OwnOccLowQuart : num 0.22 0.21 0.18 0.24 0.31 0.94 0.37 0.15 0.07 0.63 ...
## $ OwnOccMedVal : num 0.19 0.2 0.17 0.21 0.31 1 0.38 0.13 0.07 0.71 ...
## $ OwnOccHiQuart : num 0.18 0.21 0.16 0.19 0.3 1 0.39 0.13 0.08 0.79 ...
## $ RentLowQ : num 0.36 0.42 0.27 0.75 0.4 0.67 0.26 0.21 0.14 0.44 ...
## $ RentMedian : num 0.35 0.38 0.29 0.7 0.36 0.63 0.35 0.24 0.17 0.42 ...
## $ RentHighQ : num 0.38 0.4 0.27 0.77 0.38 0.68 0.42 0.25 0.16 0.47 ...
## $ MedRent : num 0.34 0.37 0.31 0.89 0.38 0.62 0.35 0.24 0.15 0.41 ...
## $ MedRentPctHousInc : num 0.38 0.29 0.48 0.63 0.22 0.47 0.46 0.64 0.38 0.23 ...
## $ MedOwnCostPctInc : num 0.46 0.32 0.39 0.51 0.51 0.59 0.44 0.59 0.13 0.27 ...
## $ MedOwnCostPctIncNoMtg: num 0.25 0.18 0.28 0.47 0.21 0.11 0.31 0.28 0.36 0.28 ...
## $ NumInShelters : num 0.04 0 0 0 0 0 0 0 0.01 0 ...
## $ NumStreet : num 0 0 0 0 0 0 0 0 0 0 ...
## $ PctForeignBorn : num 0.12 0.21 0.14 0.19 0.11 0.7 0.15 0.59 0.01 0.22 ...
## $ PctBornSameState : num 0.42 0.5 0.49 0.3 0.72 0.42 0.81 0.58 0.78 0.42 ...
## $ PctSameHouse85 : num 0.5 0.34 0.54 0.73 0.64 0.49 0.77 0.52 0.48 0.34 ...
## $ PctSameCity85 : num 0.51 0.6 0.67 0.64 0.61 0.73 0.91 0.79 0.79 0.23 ...
## $ PctSameState85 : num 0.64 0.52 0.56 0.65 0.53 0.64 0.84 0.78 0.75 0.09 ...
## $ LandArea : num 0.12 0.02 0.01 0.02 0.04 0.01 0.05 0.01 0.04 0 ...
## [list output truncated]suppressMessages(suppressWarnings(library(FactoMineR)))
suppressMessages(suppressWarnings(library(car)))
Atipicos<-(Boxplot(~ViolentCrimesPerPop, data=datos, id.method="y",col="Blue")) 
library(corrplot)
matriz.correlacion<-cor(datos)
corrplot(matriz.correlacion)
muestra <- sample(1:nrow(datos),floor(nrow(datos)*0.33))
ttesting <- datos[muestra,]
taprendizaje <- datos[-muestra,]
nrow(ttesting)## [1] 658nrow(taprendizaje)## [1] 1336modelo <- lm(ViolentCrimesPerPop ~ ., data = datos)
modelo ##
## Call:
## lm(formula = ViolentCrimesPerPop ~ ., data = datos)
##
## Coefficients:
## (Intercept) state fold
## 0.5987695 -0.0007437 -0.0015748
## population householdsize racepctblack
## 0.1321909 0.0007522 0.2000846
## racePctWhite racePctAsian racePctHisp
## -0.0545393 -0.0132278 0.0537790
## agePct12t21 agePct12t29 agePct16t24
## 0.1156000 -0.2374790 -0.1330132
## agePct65up numbUrban pctUrban
## 0.0364240 -0.2461314 0.0468133
## medIncome pctWWage pctWFarmSelf
## -0.1778505 -0.1977079 0.0466592
## pctWInvInc pctWSocSec pctWPubAsst
## -0.1600134 0.0829735 -0.0064111
## pctWRetire medFamInc perCapInc
## -0.0862223 0.2783261 0.1090832
## whitePerCap blackPerCap indianPerCap
## -0.3540081 -0.0322052 -0.0332266
## AsianPerCap OtherPerCap HispPerCap
## 0.0198696 0.0446077 0.0312484
## NumUnderPov PctPopUnderPov PctLess9thGrade
## 0.1257068 -0.1723615 -0.1019432
## PctNotHSGrad PctBSorMore PctUnemployed
## 0.0529294 0.0548989 0.0024203
## PctEmploy PctEmplManu PctEmplProfServ
## 0.2636937 -0.0611585 -0.0231200
## PctOccupManu PctOccupMgmtProf MalePctDivorce
## 0.0725969 0.1095694 0.4315918
## MalePctNevMarr FemalePctDiv TotalPctDiv
## 0.2211650 0.1139415 -0.4977383
## PersPerFam PctFam2Par PctKids2Par
## -0.1600699 -0.0143193 -0.2870569
## PctYoungKids2Par PctTeen2Par PctWorkMomYoungKids
## -0.0267124 -0.0025639 0.0523100
## PctWorkMom NumIlleg PctIlleg
## -0.1888670 -0.1383371 0.1143173
## NumImmig PctImmigRecent PctImmigRec5
## -0.1403383 0.0221218 0.0242018
## PctImmigRec8 PctImmigRec10 PctRecentImmig
## -0.0690847 0.0360765 -0.0244706
## PctRecImmig5 PctRecImmig8 PctRecImmig10
## -0.2037796 0.3916334 -0.1607644
## PctSpeakEnglOnly PctNotSpeakEnglWell PctLargHouseFam
## -0.0265885 -0.1367050 0.0572615
## PctLargHouseOccup PersPerOccupHous PersPerOwnOccHous
## -0.1874715 0.5663797 -0.0452153
## PersPerRentOccHous PctPersOwnOccup PctPersDenseHous
## -0.2410337 -0.6954982 0.2086600
## PctHousLess3BR MedNumBR HousVacant
## 0.0849002 0.0265379 0.1541798
## PctHousOccup PctHousOwnOcc PctVacantBoarded
## -0.0495127 0.5636854 0.0543938
## PctVacMore6Mos MedYrHousBuilt PctHousNoPhone
## -0.0717602 -0.0231802 0.0189781
## PctWOFullPlumb OwnOccLowQuart OwnOccMedVal
## -0.0139302 -0.3956506 0.2677203
## OwnOccHiQuart RentLowQ RentMedian
## 0.0194530 -0.2313899 -0.0012953
## RentHighQ MedRent MedRentPctHousInc
## -0.0571824 0.3417753 0.0424070
## MedOwnCostPctInc MedOwnCostPctIncNoMtg NumInShelters
## -0.0404555 -0.0739525 0.1343450
## NumStreet PctForeignBorn PctBornSameState
## 0.1754496 0.1145705 0.0166479
## PctSameHouse85 PctSameCity85 PctSameState85
## -0.0038044 0.0190145 0.0134813
## LandArea PopDens PctUsePubTrans
## 0.0176208 -0.0113547 -0.0370163
## LemasPctOfficDrugUn
## 0.0244668summary(modelo)##
## Call:
## lm(formula = ViolentCrimesPerPop ~ ., data = datos)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.49636 -0.07250 -0.01369 0.05088 0.74425
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.5987695 0.2031083 2.948 0.003237 **
## state -0.0007437 0.0002498 -2.977 0.002948 **
## fold -0.0015748 0.0010543 -1.494 0.135420
## population 0.1321909 0.3968189 0.333 0.739076
## householdsize 0.0007522 0.0865043 0.009 0.993063
## racepctblack 0.2000846 0.0510870 3.917 9.3e-05 ***
## racePctWhite -0.0545393 0.0587189 -0.929 0.353102
## racePctAsian -0.0132278 0.0343102 -0.386 0.699885
## racePctHisp 0.0537790 0.0533900 1.007 0.313926
## agePct12t21 0.1156000 0.1057256 1.093 0.274359
## agePct12t29 -0.2374790 0.1562370 -1.520 0.128680
## agePct16t24 -0.1330132 0.1639809 -0.811 0.417381
## agePct65up 0.0364240 0.1033839 0.352 0.724639
## numbUrban -0.2461314 0.3866974 -0.636 0.524530
## pctUrban 0.0468133 0.0156113 2.999 0.002747 **
## medIncome -0.1778505 0.1724501 -1.031 0.302525
## pctWWage -0.1977079 0.0894399 -2.211 0.027189 *
## pctWFarmSelf 0.0466592 0.0201155 2.320 0.020470 *
## pctWInvInc -0.1600134 0.0677020 -2.363 0.018204 *
## pctWSocSec 0.0829735 0.1069258 0.776 0.437851
## pctWPubAsst -0.0064111 0.0461302 -0.139 0.889482
## pctWRetire -0.0862223 0.0367757 -2.345 0.019153 *
## medFamInc 0.2783261 0.1601537 1.738 0.082397 .
## perCapInc 0.1090832 0.1884590 0.579 0.562782
## whitePerCap -0.3540081 0.1522613 -2.325 0.020177 *
## blackPerCap -0.0322052 0.0254324 -1.266 0.205560
## indianPerCap -0.0332266 0.0193899 -1.714 0.086766 .
## AsianPerCap 0.0198696 0.0189010 1.051 0.293279
## OtherPerCap 0.0446077 0.0186864 2.387 0.017076 *
## HispPerCap 0.0312484 0.0248313 1.258 0.208394
## NumUnderPov 0.1257068 0.1378545 0.912 0.361948
## PctPopUnderPov -0.1723615 0.0626955 -2.749 0.006031 **
## PctLess9thGrade -0.1019432 0.0677375 -1.505 0.132497
## PctNotHSGrad 0.0529294 0.0957927 0.553 0.580643
## PctBSorMore 0.0548989 0.0773171 0.710 0.477762
## PctUnemployed 0.0024203 0.0406962 0.059 0.952583
## PctEmploy 0.2636937 0.0789289 3.341 0.000851 ***
## PctEmplManu -0.0611585 0.0320386 -1.909 0.056426 .
## PctEmplProfServ -0.0231200 0.0407967 -0.567 0.570976
## PctOccupManu 0.0725969 0.0549134 1.322 0.186320
## PctOccupMgmtProf 0.1095694 0.0862375 1.271 0.204043
## MalePctDivorce 0.4315918 0.2473789 1.745 0.081207 .
## MalePctNevMarr 0.2211650 0.0678878 3.258 0.001143 **
## FemalePctDiv 0.1139415 0.3091690 0.369 0.712511
## TotalPctDiv -0.4977383 0.5179046 -0.961 0.336644
## PersPerFam -0.1600699 0.1683328 -0.951 0.341770
## PctFam2Par -0.0143193 0.1597137 -0.090 0.928570
## PctKids2Par -0.2870569 0.1555362 -1.846 0.065107 .
## PctYoungKids2Par -0.0267124 0.0481925 -0.554 0.579449
## PctTeen2Par -0.0025639 0.0425832 -0.060 0.951996
## PctWorkMomYoungKids 0.0523100 0.0469896 1.113 0.265753
## PctWorkMom -0.1888670 0.0537661 -3.513 0.000454 ***
## NumIlleg -0.1383371 0.1083610 -1.277 0.201889
## PctIlleg 0.1143173 0.0474663 2.408 0.016118 *
## NumImmig -0.1403383 0.0778895 -1.802 0.071742 .
## PctImmigRecent 0.0221218 0.0410039 0.540 0.589603
## PctImmigRec5 0.0242018 0.0664942 0.364 0.715922
## PctImmigRec8 -0.0690847 0.0770920 -0.896 0.370296
## PctImmigRec10 0.0360765 0.0595959 0.605 0.545018
## PctRecentImmig -0.0244706 0.1220592 -0.200 0.841126
## PctRecImmig5 -0.2037796 0.2211229 -0.922 0.356872
## PctRecImmig8 0.3916334 0.2731670 1.434 0.151830
## PctRecImmig10 -0.1607644 0.2188420 -0.735 0.462666
## PctSpeakEnglOnly -0.0265885 0.0702968 -0.378 0.705301
## PctNotSpeakEnglWell -0.1367050 0.0684070 -1.998 0.045816 *
## PctLargHouseFam 0.0572615 0.2258332 0.254 0.799866
## PctLargHouseOccup -0.1874715 0.2363916 -0.793 0.427845
## PersPerOccupHous 0.5663797 0.2503123 2.263 0.023768 *
## PersPerOwnOccHous -0.0452153 0.1677007 -0.270 0.787483
## PersPerRentOccHous -0.2410337 0.0808856 -2.980 0.002920 **
## PctPersOwnOccup -0.6954982 0.3576874 -1.944 0.051992 .
## PctPersDenseHous 0.2086600 0.0755707 2.761 0.005816 **
## PctHousLess3BR 0.0849002 0.0588404 1.443 0.149217
## MedNumBR 0.0265379 0.0194323 1.366 0.172207
## HousVacant 0.1541798 0.0729662 2.113 0.034729 *
## PctHousOccup -0.0495127 0.0309284 -1.601 0.109570
## PctHousOwnOcc 0.5636854 0.3740216 1.507 0.131954
## PctVacantBoarded 0.0543938 0.0214006 2.542 0.011111 *
## PctVacMore6Mos -0.0717602 0.0251453 -2.854 0.004367 **
## MedYrHousBuilt -0.0231802 0.0289186 -0.802 0.422904
## PctHousNoPhone 0.0189781 0.0352531 0.538 0.590407
## PctWOFullPlumb -0.0139302 0.0202350 -0.688 0.491271
## OwnOccLowQuart -0.3956506 0.2044847 -1.935 0.053156 .
## OwnOccMedVal 0.2677203 0.3069081 0.872 0.383148
## OwnOccHiQuart 0.0194530 0.1645854 0.118 0.905927
## RentLowQ -0.2313899 0.0669777 -3.455 0.000563 ***
## RentMedian -0.0012953 0.1565332 -0.008 0.993399
## RentHighQ -0.0571824 0.0861307 -0.664 0.506833
## MedRent 0.3417753 0.1296496 2.636 0.008454 **
## MedRentPctHousInc 0.0424070 0.0325435 1.303 0.192703
## MedOwnCostPctInc -0.0404555 0.0344644 -1.174 0.240609
## MedOwnCostPctIncNoMtg -0.0739525 0.0246266 -3.003 0.002709 **
## NumInShelters 0.1343450 0.0641192 2.095 0.036282 *
## NumStreet 0.1754496 0.0470896 3.726 0.000200 ***
## PctForeignBorn 0.1145705 0.0898118 1.276 0.202228
## PctBornSameState 0.0166479 0.0417179 0.399 0.689895
## PctSameHouse85 -0.0038044 0.0577602 -0.066 0.947492
## PctSameCity85 0.0190145 0.0381035 0.499 0.617821
## PctSameState85 0.0134813 0.0426348 0.316 0.751883
## LandArea 0.0176208 0.0490691 0.359 0.719559
## PopDens -0.0113547 0.0303202 -0.374 0.708081
## PctUsePubTrans -0.0370163 0.0231283 -1.600 0.109661
## LemasPctOfficDrugUn 0.0244668 0.0154392 1.585 0.113197
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1318 on 1891 degrees of freedom
## Multiple R-squared: 0.6965, Adjusted R-squared: 0.6801
## F-statistic: 42.54 on 102 and 1891 DF, p-value: < 2.2e-16# Calcula el modelo usando solo los datos de training
modelo.lm <- lm(ViolentCrimesPerPop~., data = taprendizaje)
modelo.lm##
## Call:
## lm(formula = ViolentCrimesPerPop ~ ., data = taprendizaje)
##
## Coefficients:
## (Intercept) state fold
## 0.7301321 -0.0005933 -0.0017368
## population householdsize racepctblack
## -0.0269510 0.1004843 0.1236990
## racePctWhite racePctAsian racePctHisp
## -0.1437003 -0.0136794 0.0632988
## agePct12t21 agePct12t29 agePct16t24
## 0.1643552 -0.1815100 -0.1828198
## agePct65up numbUrban pctUrban
## 0.0195642 -0.1106344 0.0441169
## medIncome pctWWage pctWFarmSelf
## -0.2885981 -0.1594796 0.0302056
## pctWInvInc pctWSocSec pctWPubAsst
## -0.1186551 0.0885469 -0.0189197
## pctWRetire medFamInc perCapInc
## -0.0795092 0.3339612 0.1833208
## whitePerCap blackPerCap indianPerCap
## -0.4143148 -0.0432160 -0.0329392
## AsianPerCap OtherPerCap HispPerCap
## 0.0050798 0.0291808 0.0579221
## NumUnderPov PctPopUnderPov PctLess9thGrade
## 0.1147659 -0.1817281 -0.0572288
## PctNotHSGrad PctBSorMore PctUnemployed
## 0.0424882 0.0315698 0.0096606
## PctEmploy PctEmplManu PctEmplProfServ
## 0.2326172 -0.0813150 -0.0113773
## PctOccupManu PctOccupMgmtProf MalePctDivorce
## 0.0817852 0.0899506 0.3950949
## MalePctNevMarr FemalePctDiv TotalPctDiv
## 0.0998573 0.0525902 -0.4152243
## PersPerFam PctFam2Par PctKids2Par
## -0.2326905 -0.1843596 -0.1693039
## PctYoungKids2Par PctTeen2Par PctWorkMomYoungKids
## -0.0130657 -0.0151195 0.0737985
## PctWorkMom NumIlleg PctIlleg
## -0.2160931 -0.2395280 0.1607720
## NumImmig PctImmigRecent PctImmigRec5
## -0.1207343 0.0516954 0.0117994
## PctImmigRec8 PctImmigRec10 PctRecentImmig
## -0.0904042 0.0762501 -0.0206852
## PctRecImmig5 PctRecImmig8 PctRecImmig10
## -0.4302941 0.5926712 -0.0721819
## PctSpeakEnglOnly PctNotSpeakEnglWell PctLargHouseFam
## -0.0643134 -0.1564434 0.1642796
## PctLargHouseOccup PersPerOccupHous PersPerOwnOccHous
## -0.2961117 0.5282477 0.0516878
## PersPerRentOccHous PctPersOwnOccup PctPersDenseHous
## -0.3074837 -0.9441568 0.1575127
## PctHousLess3BR MedNumBR HousVacant
## 0.0887776 0.0264781 0.2230062
## PctHousOccup PctHousOwnOcc PctVacantBoarded
## -0.0416508 0.7927967 0.0336534
## PctVacMore6Mos MedYrHousBuilt PctHousNoPhone
## -0.0716178 -0.0122728 -0.0202421
## PctWOFullPlumb OwnOccLowQuart OwnOccMedVal
## -0.0210938 -0.1794044 0.0972415
## OwnOccHiQuart RentLowQ RentMedian
## 0.0467856 -0.2278201 -0.1073302
## RentHighQ MedRent MedRentPctHousInc
## 0.0083983 0.3802668 0.0431364
## MedOwnCostPctInc MedOwnCostPctIncNoMtg NumInShelters
## -0.0552143 -0.0512172 0.2211884
## NumStreet PctForeignBorn PctBornSameState
## 0.1516897 0.0156050 -0.0006032
## PctSameHouse85 PctSameCity85 PctSameState85
## 0.0454816 0.0269999 0.0097497
## LandArea PopDens PctUsePubTrans
## 0.0064374 -0.0441963 -0.0510265
## LemasPctOfficDrugUn
## 0.0251963numero.predictoras <- dim(datos)[2] - 1
# Hace la Predicción
prediccion <- predict(modelo.lm, ttesting)
# Medición de precisión
pre.lm <- indices.precision(ttesting$ViolentCrimesPerPop, prediccion,numero.predictoras)
pre.lm## $error.cuadratico
## [1] 0.01895867
##
## $raiz.error.cuadratico
## [1] 0.1499237
##
## $error.relativo
## [1] 0.4038489
##
## $correlacion
## [1] 0.8265094# Gráfico real vs predicción, con curva de mejor ajuste lineal
library(ggplot2)
g <- plot.real.prediccion(ttesting$ViolentCrimesPerPop, prediccion, modelo = "Regresión Lineal")
g + geom_smooth(method = lm, size = 0.4, color = "red", se = FALSE)## `geom_smooth()` using formula 'y ~ x'
prediccion <- predict(modelo,datos, interval="confidence")
hist(prediccion, col = "green")
###Ridge
# La siguiente instrucción construye una matriz con los predictores
x<-model.matrix(ViolentCrimesPerPop~.,datos)
head(x)## (Intercept) state fold population householdsize racepctblack racePctWhite
## 1 1 8 1 0.19 0.33 0.02 0.90
## 2 1 53 1 0.00 0.16 0.12 0.74
## 3 1 24 1 0.00 0.42 0.49 0.56
## 4 1 34 1 0.04 0.77 1.00 0.08
## 5 1 42 1 0.01 0.55 0.02 0.95
## 6 1 6 1 0.02 0.28 0.06 0.54
## racePctAsian racePctHisp agePct12t21 agePct12t29 agePct16t24 agePct65up
## 1 0.12 0.17 0.34 0.47 0.29 0.32
## 2 0.45 0.07 0.26 0.59 0.35 0.27
## 3 0.17 0.04 0.39 0.47 0.28 0.32
## 4 0.12 0.10 0.51 0.50 0.34 0.21
## 5 0.09 0.05 0.38 0.38 0.23 0.36
## 6 1.00 0.25 0.31 0.48 0.27 0.37
## numbUrban pctUrban medIncome pctWWage pctWFarmSelf pctWInvInc pctWSocSec
## 1 0.20 1.0 0.37 0.72 0.34 0.60 0.29
## 2 0.02 1.0 0.31 0.72 0.11 0.45 0.25
## 3 0.00 0.0 0.30 0.58 0.19 0.39 0.38
## 4 0.06 1.0 0.58 0.89 0.21 0.43 0.36
## 5 0.02 0.9 0.50 0.72 0.16 0.68 0.44
## 6 0.04 1.0 0.52 0.68 0.20 0.61 0.28
## pctWPubAsst pctWRetire medFamInc perCapInc whitePerCap blackPerCap
## 1 0.15 0.43 0.39 0.40 0.39 0.32
## 2 0.29 0.39 0.29 0.37 0.38 0.33
## 3 0.40 0.84 0.28 0.27 0.29 0.27
## 4 0.20 0.82 0.51 0.36 0.40 0.39
## 5 0.11 0.71 0.46 0.43 0.41 0.28
## 6 0.15 0.25 0.62 0.72 0.76 0.77
## indianPerCap AsianPerCap OtherPerCap HispPerCap NumUnderPov PctPopUnderPov
## 1 0.27 0.27 0.36 0.41 0.08 0.19
## 2 0.16 0.30 0.22 0.35 0.01 0.24
## 3 0.07 0.29 0.28 0.39 0.01 0.27
## 4 0.16 0.25 0.36 0.44 0.01 0.10
## 5 0.00 0.74 0.51 0.48 0.00 0.06
## 6 0.28 0.52 0.48 0.60 0.01 0.12
## PctLess9thGrade PctNotHSGrad PctBSorMore PctUnemployed PctEmploy PctEmplManu
## 1 0.10 0.18 0.48 0.27 0.68 0.23
## 2 0.14 0.24 0.30 0.27 0.73 0.57
## 3 0.27 0.43 0.19 0.36 0.58 0.32
## 4 0.09 0.25 0.31 0.33 0.71 0.36
## 5 0.25 0.30 0.33 0.12 0.65 0.67
## 6 0.13 0.12 0.80 0.10 0.65 0.19
## PctEmplProfServ PctOccupManu PctOccupMgmtProf MalePctDivorce MalePctNevMarr
## 1 0.41 0.25 0.52 0.68 0.40
## 2 0.15 0.42 0.36 1.00 0.63
## 3 0.29 0.49 0.32 0.63 0.41
## 4 0.45 0.37 0.39 0.34 0.45
## 5 0.38 0.42 0.46 0.22 0.27
## 6 0.77 0.06 0.91 0.49 0.57
## FemalePctDiv TotalPctDiv PersPerFam PctFam2Par PctKids2Par PctYoungKids2Par
## 1 0.75 0.75 0.35 0.55 0.59 0.61
## 2 0.91 1.00 0.29 0.43 0.47 0.60
## 3 0.71 0.70 0.45 0.42 0.44 0.43
## 4 0.49 0.44 0.75 0.65 0.54 0.83
## 5 0.20 0.21 0.51 0.91 0.91 0.89
## 6 0.61 0.58 0.44 0.62 0.69 0.87
## PctTeen2Par PctWorkMomYoungKids PctWorkMom NumIlleg PctIlleg NumImmig
## 1 0.56 0.74 0.76 0.04 0.14 0.03
## 2 0.39 0.46 0.53 0.00 0.24 0.01
## 3 0.43 0.71 0.67 0.01 0.46 0.00
## 4 0.65 0.85 0.86 0.03 0.33 0.02
## 5 0.85 0.40 0.60 0.00 0.06 0.00
## 6 0.53 0.30 0.43 0.00 0.11 0.04
## PctImmigRecent PctImmigRec5 PctImmigRec8 PctImmigRec10 PctRecentImmig
## 1 0.24 0.27 0.37 0.39 0.07
## 2 0.52 0.62 0.64 0.63 0.25
## 3 0.07 0.06 0.15 0.19 0.02
## 4 0.11 0.20 0.30 0.31 0.05
## 5 0.03 0.07 0.20 0.27 0.01
## 6 0.30 0.35 0.43 0.47 0.50
## PctRecImmig5 PctRecImmig8 PctRecImmig10 PctSpeakEnglOnly PctNotSpeakEnglWell
## 1 0.07 0.08 0.08 0.89 0.06
## 2 0.27 0.25 0.23 0.84 0.10
## 3 0.02 0.04 0.05 0.88 0.04
## 4 0.08 0.11 0.11 0.81 0.08
## 5 0.02 0.04 0.05 0.88 0.05
## 6 0.50 0.56 0.57 0.45 0.28
## PctLargHouseFam PctLargHouseOccup PersPerOccupHous PersPerOwnOccHous
## 1 0.14 0.13 0.33 0.39
## 2 0.16 0.10 0.17 0.29
## 3 0.20 0.20 0.46 0.52
## 4 0.56 0.62 0.85 0.77
## 5 0.16 0.19 0.59 0.60
## 6 0.25 0.19 0.29 0.53
## PersPerRentOccHous PctPersOwnOccup PctPersDenseHous PctHousLess3BR MedNumBR
## 1 0.28 0.55 0.09 0.51 0.5
## 2 0.17 0.26 0.20 0.82 0.0
## 3 0.43 0.42 0.15 0.51 0.5
## 4 1.00 0.94 0.12 0.01 0.5
## 5 0.37 0.89 0.02 0.19 0.5
## 6 0.18 0.39 0.26 0.73 0.0
## HousVacant PctHousOccup PctHousOwnOcc PctVacantBoarded PctVacMore6Mos
## 1 0.21 0.71 0.52 0.05 0.26
## 2 0.02 0.79 0.24 0.02 0.25
## 3 0.01 0.86 0.41 0.29 0.30
## 4 0.01 0.97 0.96 0.60 0.47
## 5 0.01 0.89 0.87 0.04 0.55
## 6 0.02 0.84 0.30 0.16 0.28
## MedYrHousBuilt PctHousNoPhone PctWOFullPlumb OwnOccLowQuart OwnOccMedVal
## 1 0.65 0.14 0.06 0.22 0.19
## 2 0.65 0.16 0.00 0.21 0.20
## 3 0.52 0.47 0.45 0.18 0.17
## 4 0.52 0.11 0.11 0.24 0.21
## 5 0.73 0.05 0.14 0.31 0.31
## 6 0.25 0.02 0.05 0.94 1.00
## OwnOccHiQuart RentLowQ RentMedian RentHighQ MedRent MedRentPctHousInc
## 1 0.18 0.36 0.35 0.38 0.34 0.38
## 2 0.21 0.42 0.38 0.40 0.37 0.29
## 3 0.16 0.27 0.29 0.27 0.31 0.48
## 4 0.19 0.75 0.70 0.77 0.89 0.63
## 5 0.30 0.40 0.36 0.38 0.38 0.22
## 6 1.00 0.67 0.63 0.68 0.62 0.47
## MedOwnCostPctInc MedOwnCostPctIncNoMtg NumInShelters NumStreet PctForeignBorn
## 1 0.46 0.25 0.04 0 0.12
## 2 0.32 0.18 0.00 0 0.21
## 3 0.39 0.28 0.00 0 0.14
## 4 0.51 0.47 0.00 0 0.19
## 5 0.51 0.21 0.00 0 0.11
## 6 0.59 0.11 0.00 0 0.70
## PctBornSameState PctSameHouse85 PctSameCity85 PctSameState85 LandArea PopDens
## 1 0.42 0.50 0.51 0.64 0.12 0.26
## 2 0.50 0.34 0.60 0.52 0.02 0.12
## 3 0.49 0.54 0.67 0.56 0.01 0.21
## 4 0.30 0.73 0.64 0.65 0.02 0.39
## 5 0.72 0.64 0.61 0.53 0.04 0.09
## 6 0.42 0.49 0.73 0.64 0.01 0.58
## PctUsePubTrans LemasPctOfficDrugUn
## 1 0.20 0.32
## 2 0.45 0.00
## 3 0.02 0.00
## 4 0.28 0.00
## 5 0.02 0.00
## 6 0.10 0.00# Debemos eliminar la columna 1
x<-model.matrix(ViolentCrimesPerPop~.,datos)[,-c(103)]
head(x)## (Intercept) state fold population householdsize racepctblack racePctWhite
## 1 1 8 1 0.19 0.33 0.02 0.90
## 2 1 53 1 0.00 0.16 0.12 0.74
## 3 1 24 1 0.00 0.42 0.49 0.56
## 4 1 34 1 0.04 0.77 1.00 0.08
## 5 1 42 1 0.01 0.55 0.02 0.95
## 6 1 6 1 0.02 0.28 0.06 0.54
## racePctAsian racePctHisp agePct12t21 agePct12t29 agePct16t24 agePct65up
## 1 0.12 0.17 0.34 0.47 0.29 0.32
## 2 0.45 0.07 0.26 0.59 0.35 0.27
## 3 0.17 0.04 0.39 0.47 0.28 0.32
## 4 0.12 0.10 0.51 0.50 0.34 0.21
## 5 0.09 0.05 0.38 0.38 0.23 0.36
## 6 1.00 0.25 0.31 0.48 0.27 0.37
## numbUrban pctUrban medIncome pctWWage pctWFarmSelf pctWInvInc pctWSocSec
## 1 0.20 1.0 0.37 0.72 0.34 0.60 0.29
## 2 0.02 1.0 0.31 0.72 0.11 0.45 0.25
## 3 0.00 0.0 0.30 0.58 0.19 0.39 0.38
## 4 0.06 1.0 0.58 0.89 0.21 0.43 0.36
## 5 0.02 0.9 0.50 0.72 0.16 0.68 0.44
## 6 0.04 1.0 0.52 0.68 0.20 0.61 0.28
## pctWPubAsst pctWRetire medFamInc perCapInc whitePerCap blackPerCap
## 1 0.15 0.43 0.39 0.40 0.39 0.32
## 2 0.29 0.39 0.29 0.37 0.38 0.33
## 3 0.40 0.84 0.28 0.27 0.29 0.27
## 4 0.20 0.82 0.51 0.36 0.40 0.39
## 5 0.11 0.71 0.46 0.43 0.41 0.28
## 6 0.15 0.25 0.62 0.72 0.76 0.77
## indianPerCap AsianPerCap OtherPerCap HispPerCap NumUnderPov PctPopUnderPov
## 1 0.27 0.27 0.36 0.41 0.08 0.19
## 2 0.16 0.30 0.22 0.35 0.01 0.24
## 3 0.07 0.29 0.28 0.39 0.01 0.27
## 4 0.16 0.25 0.36 0.44 0.01 0.10
## 5 0.00 0.74 0.51 0.48 0.00 0.06
## 6 0.28 0.52 0.48 0.60 0.01 0.12
## PctLess9thGrade PctNotHSGrad PctBSorMore PctUnemployed PctEmploy PctEmplManu
## 1 0.10 0.18 0.48 0.27 0.68 0.23
## 2 0.14 0.24 0.30 0.27 0.73 0.57
## 3 0.27 0.43 0.19 0.36 0.58 0.32
## 4 0.09 0.25 0.31 0.33 0.71 0.36
## 5 0.25 0.30 0.33 0.12 0.65 0.67
## 6 0.13 0.12 0.80 0.10 0.65 0.19
## PctEmplProfServ PctOccupManu PctOccupMgmtProf MalePctDivorce MalePctNevMarr
## 1 0.41 0.25 0.52 0.68 0.40
## 2 0.15 0.42 0.36 1.00 0.63
## 3 0.29 0.49 0.32 0.63 0.41
## 4 0.45 0.37 0.39 0.34 0.45
## 5 0.38 0.42 0.46 0.22 0.27
## 6 0.77 0.06 0.91 0.49 0.57
## FemalePctDiv TotalPctDiv PersPerFam PctFam2Par PctKids2Par PctYoungKids2Par
## 1 0.75 0.75 0.35 0.55 0.59 0.61
## 2 0.91 1.00 0.29 0.43 0.47 0.60
## 3 0.71 0.70 0.45 0.42 0.44 0.43
## 4 0.49 0.44 0.75 0.65 0.54 0.83
## 5 0.20 0.21 0.51 0.91 0.91 0.89
## 6 0.61 0.58 0.44 0.62 0.69 0.87
## PctTeen2Par PctWorkMomYoungKids PctWorkMom NumIlleg PctIlleg NumImmig
## 1 0.56 0.74 0.76 0.04 0.14 0.03
## 2 0.39 0.46 0.53 0.00 0.24 0.01
## 3 0.43 0.71 0.67 0.01 0.46 0.00
## 4 0.65 0.85 0.86 0.03 0.33 0.02
## 5 0.85 0.40 0.60 0.00 0.06 0.00
## 6 0.53 0.30 0.43 0.00 0.11 0.04
## PctImmigRecent PctImmigRec5 PctImmigRec8 PctImmigRec10 PctRecentImmig
## 1 0.24 0.27 0.37 0.39 0.07
## 2 0.52 0.62 0.64 0.63 0.25
## 3 0.07 0.06 0.15 0.19 0.02
## 4 0.11 0.20 0.30 0.31 0.05
## 5 0.03 0.07 0.20 0.27 0.01
## 6 0.30 0.35 0.43 0.47 0.50
## PctRecImmig5 PctRecImmig8 PctRecImmig10 PctSpeakEnglOnly PctNotSpeakEnglWell
## 1 0.07 0.08 0.08 0.89 0.06
## 2 0.27 0.25 0.23 0.84 0.10
## 3 0.02 0.04 0.05 0.88 0.04
## 4 0.08 0.11 0.11 0.81 0.08
## 5 0.02 0.04 0.05 0.88 0.05
## 6 0.50 0.56 0.57 0.45 0.28
## PctLargHouseFam PctLargHouseOccup PersPerOccupHous PersPerOwnOccHous
## 1 0.14 0.13 0.33 0.39
## 2 0.16 0.10 0.17 0.29
## 3 0.20 0.20 0.46 0.52
## 4 0.56 0.62 0.85 0.77
## 5 0.16 0.19 0.59 0.60
## 6 0.25 0.19 0.29 0.53
## PersPerRentOccHous PctPersOwnOccup PctPersDenseHous PctHousLess3BR MedNumBR
## 1 0.28 0.55 0.09 0.51 0.5
## 2 0.17 0.26 0.20 0.82 0.0
## 3 0.43 0.42 0.15 0.51 0.5
## 4 1.00 0.94 0.12 0.01 0.5
## 5 0.37 0.89 0.02 0.19 0.5
## 6 0.18 0.39 0.26 0.73 0.0
## HousVacant PctHousOccup PctHousOwnOcc PctVacantBoarded PctVacMore6Mos
## 1 0.21 0.71 0.52 0.05 0.26
## 2 0.02 0.79 0.24 0.02 0.25
## 3 0.01 0.86 0.41 0.29 0.30
## 4 0.01 0.97 0.96 0.60 0.47
## 5 0.01 0.89 0.87 0.04 0.55
## 6 0.02 0.84 0.30 0.16 0.28
## MedYrHousBuilt PctHousNoPhone PctWOFullPlumb OwnOccLowQuart OwnOccMedVal
## 1 0.65 0.14 0.06 0.22 0.19
## 2 0.65 0.16 0.00 0.21 0.20
## 3 0.52 0.47 0.45 0.18 0.17
## 4 0.52 0.11 0.11 0.24 0.21
## 5 0.73 0.05 0.14 0.31 0.31
## 6 0.25 0.02 0.05 0.94 1.00
## OwnOccHiQuart RentLowQ RentMedian RentHighQ MedRent MedRentPctHousInc
## 1 0.18 0.36 0.35 0.38 0.34 0.38
## 2 0.21 0.42 0.38 0.40 0.37 0.29
## 3 0.16 0.27 0.29 0.27 0.31 0.48
## 4 0.19 0.75 0.70 0.77 0.89 0.63
## 5 0.30 0.40 0.36 0.38 0.38 0.22
## 6 1.00 0.67 0.63 0.68 0.62 0.47
## MedOwnCostPctInc MedOwnCostPctIncNoMtg NumInShelters NumStreet PctForeignBorn
## 1 0.46 0.25 0.04 0 0.12
## 2 0.32 0.18 0.00 0 0.21
## 3 0.39 0.28 0.00 0 0.14
## 4 0.51 0.47 0.00 0 0.19
## 5 0.51 0.21 0.00 0 0.11
## 6 0.59 0.11 0.00 0 0.70
## PctBornSameState PctSameHouse85 PctSameCity85 PctSameState85 LandArea PopDens
## 1 0.42 0.50 0.51 0.64 0.12 0.26
## 2 0.50 0.34 0.60 0.52 0.02 0.12
## 3 0.49 0.54 0.67 0.56 0.01 0.21
## 4 0.30 0.73 0.64 0.65 0.02 0.39
## 5 0.72 0.64 0.61 0.53 0.04 0.09
## 6 0.42 0.49 0.73 0.64 0.01 0.58
## PctUsePubTrans
## 1 0.20
## 2 0.45
## 3 0.02
## 4 0.28
## 5 0.02
## 6 0.10# La siguiente instrucción construye la variable a predecir
y<-datos$ViolentCrimesPerPoplibrary(glmnet)ridge.mod<-glmnet(x,y,alpha=0)
dim(coef(ridge.mod))## [1] 103 100coef(ridge.mod)## 103 x 100 sparse Matrix of class "dgCMatrix"## [[ suppressing 100 column names 's0', 's1', 's2' ... ]]##
## (Intercept) 2.379789e-01 2.401887e-01 2.403942e-01 2.406177e-01
## (Intercept) . . . .
## state -3.033985e-39 -4.411398e-06 -4.835893e-06 -5.300705e-06
## fold -2.667833e-39 -3.831321e-06 -4.194991e-06 -4.592408e-06
## population 6.808685e-37 9.746098e-04 1.066772e-03 1.167395e-03
## householdsize -5.020027e-38 -7.384222e-05 -8.104090e-05 -8.893632e-05
## racepctblack 5.861715e-37 8.434881e-04 9.237309e-04 1.011439e-03
## racePctWhite -6.603544e-37 -9.472854e-04 -1.037089e-03 -1.135185e-03
## racePctAsian 4.238776e-38 6.324903e-05 6.950474e-05 7.637546e-05
## racePctHisp 2.966384e-37 4.200841e-04 4.593238e-04 5.020800e-04
## agePct12t21 9.170750e-38 1.215352e-04 1.319847e-04 1.432130e-04
## agePct12t29 2.513919e-37 3.483904e-04 3.801112e-04 4.145254e-04
## agePct16t24 1.404170e-37 1.918786e-04 2.090512e-04 2.276248e-04
## agePct65up 8.822151e-38 1.257556e-04 1.375868e-04 1.505019e-04
## numbUrban 6.658835e-37 9.543828e-04 1.044773e-03 1.143476e-03
## pctUrban 4.339763e-38 6.582533e-05 7.244832e-05 7.974827e-05
## medIncome -4.768540e-37 -6.714527e-04 -7.337628e-04 -8.015900e-04
## pctWWage -3.930613e-37 -5.574936e-04 -6.096669e-04 -6.665394e-04
## pctWFarmSelf -1.765541e-37 -2.562046e-04 -2.808054e-04 -3.077312e-04
## pctWInvInc -7.616699e-37 -1.082114e-03 -1.183586e-03 -1.294225e-03
## pctWSocSec 1.599169e-37 2.256988e-04 2.467021e-04 2.695772e-04
## pctWPubAsst 6.088175e-37 8.654274e-04 9.466341e-04 1.035181e-03
## pctWRetire -1.382592e-37 -1.970227e-04 -2.155636e-04 -2.357871e-04
## medFamInc -5.212376e-37 -7.346384e-04 -8.029026e-04 -8.772129e-04
## perCapInc -4.335705e-37 -6.079549e-04 -6.641142e-04 -7.251823e-04
## whitePerCap -2.636438e-37 -3.633597e-04 -3.962432e-04 -4.318697e-04
## blackPerCap -3.776955e-37 -5.315993e-04 -5.809274e-04 -6.346050e-04
## indianPerCap -1.297608e-37 -1.809827e-04 -1.975996e-04 -2.156481e-04
## AsianPerCap -1.873830e-37 -2.600912e-04 -2.838313e-04 -3.095877e-04
## OtherPerCap -1.555015e-37 -2.148030e-04 -2.342964e-04 -2.554236e-04
## HispPerCap -3.143569e-37 -4.385148e-04 -4.787816e-04 -5.225138e-04
## NumUnderPov 8.232953e-37 1.176392e-03 1.287440e-03 1.408626e-03
## PctPopUnderPov 5.375555e-37 7.614053e-04 8.325766e-04 9.101143e-04
## PctLess9thGrade 4.534435e-37 6.404940e-04 7.001730e-04 7.651535e-04
## PctNotHSGrad 5.617285e-37 7.958449e-04 8.702608e-04 9.513351e-04
## PctBSorMore -3.540036e-37 -4.988377e-04 -5.451977e-04 -5.956493e-04
## PctUnemployed 5.869563e-37 8.321810e-04 9.100605e-04 9.949162e-04
## PctEmploy -4.484594e-37 -6.339463e-04 -6.930805e-04 -7.574710e-04
## PctEmplManu -5.221756e-38 -7.760571e-05 -8.524785e-05 -9.364773e-05
## PctEmplProfServ -9.587876e-38 -1.363901e-04 -1.492016e-04 -1.631716e-04
## PctOccupManu 3.496926e-37 4.916738e-04 5.372553e-04 5.868334e-04
## PctOccupMgmtProf -4.283892e-37 -6.028657e-04 -6.588151e-04 -7.196796e-04
## MalePctDivorce 6.776730e-37 9.686741e-04 1.060169e-03 1.160022e-03
## MalePctNevMarr 4.085791e-37 5.814919e-04 6.361404e-04 6.957287e-04
## FemalePctDiv 7.470215e-37 1.067299e-03 1.168055e-03 1.278005e-03
## TotalPctDiv 7.085240e-37 1.012464e-03 1.108066e-03 1.212392e-03
## PersPerFam 2.141132e-37 3.046091e-04 3.332271e-04 3.644286e-04
## PctFam2Par -8.233935e-37 -1.175747e-03 -1.286680e-03 -1.407715e-03
## PctKids2Par -8.421443e-37 -1.203170e-03 -1.316761e-03 -1.440709e-03
## PctYoungKids2Par -7.165698e-37 -1.022532e-03 -1.118944e-03 -1.224118e-03
## PctTeen2Par -8.130017e-37 -1.162170e-03 -1.271960e-03 -1.391771e-03
## PctWorkMomYoungKids -3.145356e-38 -4.503986e-05 -4.929633e-05 -5.394367e-05
## PctWorkMom -2.021903e-37 -2.888493e-04 -3.161124e-04 -3.458608e-04
## NumIlleg 1.020060e-36 1.461189e-03 1.599532e-03 1.750561e-03
## PctIlleg 7.552614e-37 1.082208e-03 1.184716e-03 1.296634e-03
## NumImmig 7.942007e-37 1.133180e-03 1.239979e-03 1.356476e-03
## PctImmigRecent 1.846260e-37 2.605066e-04 2.847515e-04 3.111392e-04
## PctImmigRec5 2.410562e-37 3.406943e-04 3.724638e-04 4.070522e-04
## PctImmigRec8 2.898080e-37 4.108815e-04 4.493339e-04 4.912248e-04
## PctImmigRec10 3.518986e-37 4.997445e-04 5.466037e-04 5.976701e-04
## PctRecentImmig 2.303250e-37 3.281145e-04 3.589803e-04 3.926389e-04
## PctRecImmig5 2.470006e-37 3.521309e-04 3.852854e-04 4.214445e-04
## PctRecImmig8 2.516992e-37 3.593073e-04 3.931890e-04 4.301507e-04
## PctRecImmig10 2.648438e-37 3.781797e-04 4.138538e-04 4.527726e-04
## PctSpeakEnglOnly -2.504801e-37 -3.553820e-04 -3.886660e-04 -4.249293e-04
## PctNotSpeakEnglWell 3.213509e-37 4.554343e-04 4.980396e-04 5.444476e-04
## PctLargHouseFam 4.591175e-37 6.536774e-04 7.151538e-04 7.821830e-04
## PctLargHouseOccup 3.637942e-37 5.173898e-04 5.659894e-04 6.189661e-04
## PersPerOccupHous -5.515811e-38 -7.816894e-05 -8.548157e-05 -9.344769e-05
## PersPerOwnOccHous -1.854046e-37 -2.649034e-04 -2.899175e-04 -3.172121e-04
## PersPerRentOccHous 3.087352e-37 4.388333e-04 4.800291e-04 5.249305e-04
## PctPersOwnOccup -6.274799e-37 -8.909012e-04 -9.744264e-04 -1.065443e-03
## PctPersDenseHous 5.076525e-37 7.222647e-04 7.901376e-04 8.641288e-04
## PctHousLess3BR 6.473066e-37 9.189735e-04 1.005122e-03 1.098995e-03
## MedNumBR -3.295940e-37 -4.670888e-04 -5.107872e-04 -5.583852e-04
## HousVacant 6.590959e-37 9.452846e-04 1.034910e-03 1.132774e-03
## PctHousOccup -3.869374e-37 -5.534189e-04 -6.057368e-04 -6.628345e-04
## PctHousOwnOcc -5.980952e-37 -8.483939e-04 -9.278518e-04 -1.014417e-03
## PctVacantBoarded 5.217656e-37 7.467312e-04 8.173721e-04 8.944755e-04
## PctVacMore6Mos 2.650289e-38 3.546443e-05 3.856491e-05 4.189909e-05
## MedYrHousBuilt -1.113531e-37 -1.572228e-04 -1.718694e-04 -1.878099e-04
## PctHousNoPhone 4.731472e-37 6.712874e-04 7.341793e-04 8.027026e-04
## PctWOFullPlumb 4.157637e-37 5.893702e-04 6.445304e-04 7.046172e-04
## OwnOccLowQuart -2.207887e-37 -3.081783e-04 -3.365214e-04 -3.672963e-04
## OwnOccMedVal -1.938511e-37 -2.696782e-04 -2.943845e-04 -3.211907e-04
## OwnOccHiQuart -1.721850e-37 -2.385527e-04 -2.603020e-04 -2.838782e-04
## RentLowQ -2.702377e-37 -3.787034e-04 -4.136927e-04 -4.517162e-04
## RentMedian -2.704412e-37 -3.774597e-04 -4.121703e-04 -4.498573e-04
## RentHighQ -2.201768e-37 -3.069559e-04 -3.351457e-04 -3.657452e-04
## MedRent -2.645172e-37 -3.684966e-04 -4.023071e-04 -4.390013e-04
## MedRentPctHousInc 4.513019e-37 6.439372e-04 7.046449e-04 7.708634e-04
## MedOwnCostPctInc 8.023320e-38 1.196257e-04 1.314370e-04 1.444263e-04
## MedOwnCostPctIncNoMtg 6.569571e-38 9.341161e-05 1.021826e-04 1.117423e-04
## NumInShelters 8.618281e-37 1.234493e-03 1.351375e-03 1.478966e-03
## NumStreet 7.976102e-37 1.144582e-03 1.253170e-03 1.371752e-03
## PctForeignBorn 1.979262e-37 2.835744e-04 3.104242e-04 3.397331e-04
## PctBornSameState -8.886896e-38 -1.307974e-04 -1.435431e-04 -1.575280e-04
## PctSameHouse85 -2.016454e-37 -2.841717e-04 -3.105888e-04 -3.393288e-04
## PctSameCity85 8.867718e-38 1.289116e-04 1.413183e-04 1.549027e-04
## PctSameState85 -2.310264e-38 -3.365665e-05 -3.689941e-05 -4.044995e-05
## LandArea 4.231217e-37 6.072336e-04 6.648465e-04 7.277619e-04
## PopDens 3.260679e-37 4.659629e-04 5.099619e-04 5.579677e-04
## PctUsePubTrans 1.580487e-37 2.296451e-04 2.517242e-04 2.758926e-04
##
## (Intercept) 2.408608e-01 2.411248e-01 2.414112e-01 2.417218e-01
## (Intercept) . . . .
## state -5.809497e-06 -6.366290e-06 -6.975449e-06 -7.641702e-06
## fold -5.026316e-06 -5.499845e-06 -6.016354e-06 -6.579440e-06
## population 1.277161e-03 1.396835e-03 1.527228e-03 1.669205e-03
## householdsize -9.759961e-05 -1.071050e-04 -1.175339e-04 -1.289751e-04
## racepctblack 1.107236e-03 1.211823e-03 1.325952e-03 1.450430e-03
## racePctWhite -1.242253e-03 -1.359055e-03 -1.486404e-03 -1.625171e-03
## racePctAsian 8.393138e-05 9.224127e-05 1.013807e-04 1.114325e-04
## racePctHisp 5.486080e-04 5.991996e-04 6.541615e-04 7.138138e-04
## agePct12t21 1.552188e-04 1.680184e-04 1.816192e-04 1.960173e-04
## agePct12t29 4.517798e-04 4.920537e-04 5.355265e-04 5.823748e-04
## agePct16t24 2.476580e-04 2.692266e-04 2.924024e-04 3.172503e-04
## agePct65up 1.645788e-04 1.799125e-04 1.966036e-04 2.147590e-04
## numbUrban 1.251180e-03 1.368642e-03 1.496671e-03 1.636127e-03
## pctUrban 8.780469e-05 9.669937e-05 1.065234e-04 1.173784e-04
## medIncome -8.753072e-04 -9.553519e-04 -1.042180e-03 -1.136262e-03
## pctWWage -7.284557e-04 -7.958129e-04 -8.690290e-04 -9.485432e-04
## pctWFarmSelf -3.371917e-04 -3.694159e-04 -4.046520e-04 -4.431678e-04
## pctWInvInc -1.414723e-03 -1.545864e-03 -1.688478e-03 -1.843437e-03
## pctWSocSec 2.944539e-04 3.214843e-04 3.508276e-04 3.826496e-04
## pctWPubAsst 1.131630e-03 1.236610e-03 1.350790e-03 1.474872e-03
## pctWRetire -2.578268e-04 -2.818299e-04 -3.079527e-04 -3.363602e-04
## medFamInc -9.579953e-04 -1.045735e-03 -1.140937e-03 -1.244127e-03
## perCapInc -7.914889e-04 -8.634098e-04 -9.413333e-04 -1.025658e-03
## whitePerCap -4.703871e-04 -5.119679e-04 -5.567822e-04 -6.049939e-04
## blackPerCap -6.929404e-04 -7.562794e-04 -8.249820e-04 -8.994205e-04
## indianPerCap -2.352204e-04 -2.564209e-04 -2.793561e-04 -3.041342e-04
## AsianPerCap -3.374829e-04 -3.676553e-04 -4.002441e-04 -4.353876e-04
## OtherPerCap -2.782774e-04 -3.029636e-04 -3.295869e-04 -3.582492e-04
## HispPerCap -5.699369e-04 -6.213029e-04 -6.768687e-04 -7.368941e-04
## NumUnderPov 1.540775e-03 1.684794e-03 1.841645e-03 2.012353e-03
## PctPopUnderPov 9.945026e-04 1.086275e-03 1.185993e-03 1.294244e-03
## PctLess9thGrade 8.358293e-04 9.126342e-04 9.960227e-04 1.086468e-03
## PctNotHSGrad 1.039578e-03 1.135550e-03 1.239839e-03 1.353062e-03
## PctBSorMore -6.504941e-04 -7.100615e-04 -7.746948e-04 -8.447506e-04
## PctUnemployed 1.087290e-03 1.187770e-03 1.296979e-03 1.415567e-03
## PctEmploy -8.275196e-04 -9.036609e-04 -9.863507e-04 -1.076064e-03
## PctEmplManu -1.028824e-04 -1.130360e-04 -1.242008e-04 -1.364787e-04
## PctEmplProfServ -1.783911e-04 -1.949607e-04 -2.129866e-04 -2.325813e-04
## PctOccupManu 6.407005e-04 6.991723e-04 7.625766e-04 8.312520e-04
## PctOccupMgmtProf -7.858235e-04 -8.576381e-04 -9.355306e-04 -1.019922e-03
## MalePctDivorce 1.268924e-03 1.387626e-03 1.516929e-03 1.657683e-03
## MalePctNevMarr 7.606498e-04 8.313325e-04 9.082309e-04 9.918236e-04
## FemalePctDiv 1.397903e-03 1.528576e-03 1.670898e-03 1.825801e-03
## TotalPctDiv 1.326163e-03 1.450163e-03 1.585226e-03 1.732236e-03
## PersPerFam 3.984205e-04 4.354269e-04 4.756851e-04 5.194453e-04
## PctFam2Par -1.539690e-03 -1.683504e-03 -1.840120e-03 -2.010556e-03
## PctKids2Par -1.575876e-03 -1.723189e-03 -1.883639e-03 -2.058275e-03
## PctYoungKids2Par -1.338781e-03 -1.463712e-03 -1.599741e-03 -1.747747e-03
## PctTeen2Par -1.522440e-03 -1.664872e-03 -1.820026e-03 -1.988925e-03
## PctWorkMomYoungKids -5.901190e-05 -6.453559e-05 -7.055136e-05 -7.709791e-05
## PctWorkMom -3.782991e-04 -4.136492e-04 -4.521472e-04 -4.940435e-04
## NumIlleg 1.915348e-03 2.095048e-03 2.290897e-03 2.504207e-03
## PctIlleg 1.418760e-03 1.551957e-03 1.697146e-03 1.855307e-03
## NumImmig 1.483465e-03 1.621802e-03 1.772395e-03 1.936206e-03
## PctImmigRecent 3.398310e-04 3.710003e-04 4.048284e-04 4.415032e-04
## PctImmigRec5 4.446755e-04 4.855653e-04 5.299641e-04 5.781246e-04
## PctImmigRec8 5.368248e-04 5.864237e-04 6.403270e-04 6.988544e-04
## PctImmigRec10 6.532797e-04 7.137925e-04 7.795883e-04 8.510661e-04
## PctRecentImmig 4.293147e-04 4.692509e-04 5.127048e-04 5.599477e-04
## PctRecImmig5 4.608521e-04 5.037715e-04 5.504816e-04 6.012771e-04
## PctRecImmig8 4.704452e-04 5.143452e-04 5.621402e-04 6.141366e-04
## PctRecImmig10 4.952038e-04 5.414355e-04 5.917735e-04 6.465418e-04
## PctSpeakEnglOnly -4.644079e-04 -5.073541e-04 -5.540335e-04 -6.047239e-04
## PctNotSpeakEnglWell 5.949591e-04 6.498939e-04 7.095879e-04 7.743929e-04
## PctLargHouseFam 8.552199e-04 9.347500e-04 1.021287e-03 1.115375e-03
## PctLargHouseOccup 6.766766e-04 7.395005e-04 8.078393e-04 8.821161e-04
## PersPerOccupHous -1.021186e-04 -1.115494e-04 -1.217980e-04 -1.329251e-04
## PersPerOwnOccHous -3.469782e-04 -3.794209e-04 -4.147587e-04 -4.532236e-04
## PersPerRentOccHous 5.738387e-04 6.270740e-04 6.849752e-04 7.478990e-04
## PctPersOwnOccup -1.164554e-03 -1.272401e-03 -1.389661e-03 -1.517045e-03
## PctPersDenseHous 9.447383e-04 1.032498e-03 1.127971e-03 1.231751e-03
## PctHousLess3BR 1.201214e-03 1.312440e-03 1.433369e-03 1.564735e-03
## MedNumBR -6.101935e-04 -6.665406e-04 -7.277724e-04 -7.942509e-04
## HousVacant 1.239583e-03 1.356093e-03 1.483115e-03 1.621513e-03
## PctHousOccup -7.251163e-04 -7.930148e-04 -8.669917e-04 -9.475383e-04
## PctHousOwnOcc -1.108661e-03 -1.211188e-03 -1.322633e-03 -1.443664e-03
## PctVacantBoarded 9.785901e-04 1.070303e-03 1.170241e-03 1.279072e-03
## PctVacMore6Mos 4.547703e-05 4.930760e-05 5.339802e-05 5.775329e-05
## MedYrHousBuilt -2.051449e-04 -2.239801e-04 -2.444257e-04 -2.665963e-04
## PctHousNoPhone 8.773115e-04 9.584865e-04 1.046735e-03 1.142591e-03
## PctWOFullPlumb 7.700253e-04 8.411716e-04 9.184951e-04 1.002456e-03
## OwnOccLowQuart -4.006782e-04 -4.368478e-04 -4.759905e-04 -5.182946e-04
## OwnOccMedVal -3.502443e-04 -3.816961e-04 -4.156993e-04 -4.524086e-04
## OwnOccHiQuart -3.094050e-04 -3.370076e-04 -3.668122e-04 -3.989439e-04
## RentLowQ -4.929996e-04 -5.377770e-04 -5.862904e-04 -6.387884e-04
## RentMedian -4.907352e-04 -5.350244e-04 -5.829510e-04 -6.347445e-04
## RentHighQ -3.989263e-04 -4.348655e-04 -4.737432e-04 -5.157419e-04
## MedRent -4.787833e-04 -5.218623e-04 -5.684517e-04 -6.187669e-04
## MedRentPctHousInc 8.430518e-04 9.216993e-04 1.007326e-03 1.100482e-03
## MedOwnCostPctInc 1.587122e-04 1.744258e-04 1.917113e-04 2.107273e-04
## MedOwnCostPctIncNoMtg 1.221550e-04 1.334885e-04 1.458147e-04 1.592090e-04
## NumInShelters 1.618177e-03 1.769985e-03 1.935430e-03 2.115622e-03
## NumStreet 1.501186e-03 1.642396e-03 1.796367e-03 1.964153e-03
## PctForeignBorn 3.717099e-04 4.065776e-04 4.445744e-04 4.859530e-04
## PctBornSameState -1.728715e-04 -1.897041e-04 -2.081685e-04 -2.284207e-04
## PctSameHouse85 -3.705701e-04 -4.044994e-04 -4.413114e-04 -4.812076e-04
## PctSameCity85 1.697735e-04 1.860489e-04 2.038570e-04 2.233372e-04
## PctSameState85 -4.433635e-05 -4.858904e-05 -5.324091e-05 -5.832741e-05
## LandArea 7.964360e-04 8.713579e-04 9.530510e-04 1.042074e-03
## PopDens 6.103165e-04 6.673668e-04 7.294998e-04 7.971200e-04
## PctUsePubTrans 3.023410e-04 3.312761e-04 3.629218e-04 3.975198e-04
##
## (Intercept) 2.420581e-01 2.424218e-01 2.428146e-01 2.432383e-01
## (Intercept) . . . .
## state -8.370163e-06 -9.166362e-06 -1.003626e-05 -1.098630e-05
## fold -7.192945e-06 -7.860966e-06 -8.587862e-06 -9.378253e-06
## population 1.823683e-03 1.991629e-03 2.174057e-03 2.372030e-03
## householdsize -1.415260e-04 -1.552929e-04 -1.703920e-04 -1.869500e-04
## racepctblack 1.586119e-03 1.733941e-03 1.894876e-03 2.069965e-03
## racePctWhite -1.776282e-03 -1.940719e-03 -2.119523e-03 -2.313789e-03
## racePctAsian 1.224876e-04 1.346453e-04 1.480141e-04 1.627124e-04
## racePctHisp 7.784891e-04 8.485304e-04 9.242885e-04 1.006119e-03
## agePct12t21 2.111944e-04 2.271143e-04 2.437185e-04 2.609222e-04
## agePct12t29 6.327684e-04 6.868665e-04 7.448119e-04 8.067255e-04
## agePct16t24 3.438254e-04 3.721698e-04 4.023087e-04 4.342454e-04
## agePct65up 2.344911e-04 2.559183e-04 2.791644e-04 3.043583e-04
## numbUrban 1.787926e-03 1.953033e-03 2.132470e-03 2.327304e-03
## pctUrban 1.293773e-04 1.426461e-04 1.573252e-04 1.735709e-04
## medIncome -1.238083e-03 -1.348135e-03 -1.466914e-03 -1.594914e-03
## pctWWage -1.034814e-03 -1.128317e-03 -1.229545e-03 -1.339000e-03
## pctWFarmSelf -4.852528e-04 -5.312186e-04 -5.814002e-04 -6.361574e-04
## pctWInvInc -2.011657e-03 -2.194092e-03 -2.391728e-03 -2.605585e-03
## pctWSocSec 4.171220e-04 4.544211e-04 4.947267e-04 5.382204e-04
## pctWPubAsst 1.609593e-03 1.755723e-03 1.914059e-03 2.085422e-03
## pctWRetire -3.672261e-04 -4.007324e-04 -4.370686e-04 -4.764312e-04
## medFamInc -1.355845e-03 -1.476643e-03 -1.607079e-03 -1.747711e-03
## perCapInc -1.116787e-03 -1.215128e-03 -1.321082e-03 -1.435042e-03
## whitePerCap -6.567569e-04 -7.122104e-04 -7.714723e-04 -8.346333e-04
## blackPerCap -9.799776e-04 -1.067043e-03 -1.161009e-03 -1.262268e-03
## indianPerCap -3.308629e-04 -3.596486e-04 -3.905940e-04 -4.237961e-04
## AsianPerCap -4.732208e-04 -5.138719e-04 -5.574595e-04 -6.040880e-04
## OtherPerCap -3.890474e-04 -4.220704e-04 -4.573957e-04 -4.950858e-04
## HispPerCap -8.016379e-04 -8.713543e-04 -9.462875e-04 -1.026666e-03
## NumUnderPov 2.197996e-03 2.399713e-03 2.618697e-03 2.856193e-03
## PctPopUnderPov 1.411639e-03 1.538813e-03 1.676417e-03 1.825113e-03
## PctLess9thGrade 1.184460e-03 1.290500e-03 1.405103e-03 1.528784e-03
## PctNotHSGrad 1.475863e-03 1.608907e-03 1.752879e-03 1.908481e-03
## PctBSorMore -9.205959e-04 -1.002606e-03 -1.091161e-03 -1.186640e-03
## PctUnemployed 1.544215e-03 1.683627e-03 1.834530e-03 1.997668e-03
## PctEmploy -1.173296e-03 -1.278553e-03 -1.392356e-03 -1.515232e-03
## PctEmplManu -1.499820e-04 -1.648339e-04 -1.811703e-04 -1.991403e-04
## PctEmplProfServ -2.538626e-04 -2.769540e-04 -3.019840e-04 -3.290853e-04
## PctOccupManu 9.055452e-04 9.858081e-04 1.072394e-03 1.165654e-03
## PctOccupMgmtProf -1.111245e-03 -1.209940e-03 -1.316450e-03 -1.431216e-03
## MalePctDivorce 1.810790e-03 1.977202e-03 2.157918e-03 2.353986e-03
## MalePctNevMarr 1.082613e-03 1.181125e-03 1.287903e-03 1.403512e-03
## FemalePctDiv 1.994269e-03 2.177342e-03 2.376110e-03 2.591712e-03
## TotalPctDiv 1.892132e-03 2.065902e-03 2.254585e-03 2.459267e-03
## PersPerFam 5.669702e-04 6.185343e-04 6.744232e-04 7.349315e-04
## PctFam2Par -2.195889e-03 -2.397256e-03 -2.615848e-03 -2.852909e-03
## PctKids2Par -2.248211e-03 -2.454619e-03 -2.678732e-03 -2.921839e-03
## PctYoungKids2Par -1.908658e-03 -2.083452e-03 -2.273154e-03 -2.478833e-03
## PctTeen2Par -2.172651e-03 -2.372349e-03 -2.589218e-03 -2.824519e-03
## PctWorkMomYoungKids -8.421585e-05 -9.194757e-05 -1.003370e-04 -1.094294e-04
## PctWorkMom -5.396027e-04 -5.891033e-04 -6.428371e-04 -7.011085e-04
## NumIlleg 2.736375e-03 2.988877e-03 3.263270e-03 3.561187e-03
## PctIlleg 2.027485e-03 2.214788e-03 2.418385e-03 2.639508e-03
## NumImmig 2.114245e-03 2.307572e-03 2.517293e-03 2.744553e-03
## PctImmigRecent 4.812182e-04 5.241713e-04 5.705627e-04 6.205924e-04
## PctImmigRec5 6.303078e-04 6.867821e-04 7.478203e-04 8.136974e-04
## PctImmigRec8 7.623390e-04 8.311259e-04 9.055697e-04 9.860319e-04
## PctImmigRec10 9.286435e-04 1.012754e-03 1.103847e-03 1.202382e-03
## PctRecentImmig 6.112642e-04 6.669516e-04 7.273179e-04 7.926806e-04
## PctRecImmig5 6.564676e-04 7.163768e-04 7.813414e-04 8.517092e-04
## PctRecImmig8 6.706569e-04 7.320396e-04 7.986380e-04 8.708181e-04
## PctRecImmig10 7.060819e-04 7.707524e-04 8.409275e-04 9.169960e-04
## PctSpeakEnglOnly -6.597153e-04 -7.193075e-04 -7.838089e-04 -8.535336e-04
## PctNotSpeakEnglWell 8.446746e-04 9.208110e-04 1.003190e-03 1.092206e-03
## PctLargHouseFam 1.217585e-03 1.328513e-03 1.448784e-03 1.579040e-03
## PctLargHouseOccup 9.627752e-04 1.050280e-03 1.145113e-03 1.247771e-03
## PersPerOccupHous -1.449938e-04 -1.580697e-04 -1.722200e-04 -1.875132e-04
## PersPerOwnOccHous -4.950618e-04 -5.405326e-04 -5.899093e-04 -6.434777e-04
## PersPerRentOccHous 8.162196e-04 8.903279e-04 9.706291e-04 1.057542e-03
## PctPersOwnOccup -1.655296e-03 -1.805189e-03 -1.967524e-03 -2.143122e-03
## PctPersDenseHous 1.344461e-03 1.466752e-03 1.599303e-03 1.742811e-03
## PctHousLess3BR 1.707302e-03 1.861867e-03 2.029253e-03 2.210304e-03
## MedNumBR -8.663531e-04 -9.444695e-04 -1.029001e-03 -1.120357e-03
## HousVacant 1.772205e-03 1.936167e-03 2.114428e-03 2.308074e-03
## PctHousOccup -1.035176e-03 -1.130455e-03 -1.233956e-03 -1.346290e-03
## PctHousOwnOcc -1.574978e-03 -1.717299e-03 -1.871373e-03 -2.037962e-03
## PctVacantBoarded 1.397503e-03 1.526286e-03 1.666209e-03 1.818103e-03
## PctVacMore6Mos 6.237562e-05 6.726363e-05 7.241162e-05 7.780856e-05
## MedYrHousBuilt -2.906102e-04 -3.165883e-04 -3.446531e-04 -3.749275e-04
## PctHousNoPhone 1.246610e-03 1.359375e-03 1.481484e-03 1.613555e-03
## PctWOFullPlumb 1.093536e-03 1.192231e-03 1.299055e-03 1.414532e-03
## OwnOccLowQuart -5.639495e-04 -6.131432e-04 -6.660591e-04 -7.228727e-04
## OwnOccMedVal -4.919774e-04 -5.345555e-04 -5.802865e-04 -6.293039e-04
## OwnOccHiQuart -4.335249e-04 -4.706718e-04 -5.104927e-04 -5.530835e-04
## RentLowQ -6.955236e-04 -7.567506e-04 -8.227224e-04 -8.936870e-04
## RentMedian -6.906351e-04 -7.508512e-04 -8.156145e-04 -8.851365e-04
## RentHighQ -5.610442e-04 -6.098298e-04 -6.622727e-04 -7.185368e-04
## MedRent -6.730224e-04 -7.314284e-04 -7.941869e-04 -8.614869e-04
## MedRentPctHousInc 1.201750e-03 1.311739e-03 1.431089e-03 1.560466e-03
## MedOwnCostPctInc 2.316484e-04 2.546664e-04 2.799918e-04 3.078553e-04
## MedOwnCostPctIncNoMtg 1.737504e-04 1.895211e-04 2.066060e-04 2.250922e-04
## NumInShelters 2.311736e-03 2.525019e-03 2.756782e-03 3.008400e-03
## NumStreet 2.146874e-03 2.345719e-03 2.561948e-03 2.796886e-03
## PctForeignBorn 5.309814e-04 5.799423e-04 6.331325e-04 6.908621e-04
## PctBornSameState -2.506305e-04 -2.749831e-04 -3.016801e-04 -3.309402e-04
## PctSameHouse85 -5.243953e-04 -5.710855e-04 -6.214911e-04 -6.758241e-04
## PctSameCity85 2.446404e-04 2.679300e-04 2.933830e-04 3.211904e-04
## PctSameState85 -6.388665e-05 -6.995950e-05 -7.658962e-05 -8.382349e-05
## LandArea 1.139021e-03 1.244522e-03 1.359246e-03 1.483893e-03
## PopDens 8.706546e-04 9.505529e-04 1.037286e-03 1.131343e-03
## PctUsePubTrans 4.353312e-04 4.766367e-04 5.217384e-04 5.709598e-04
##
## (Intercept) 2.436945e-01 2.441850e-01 2.447113e-01 2.452750e-01
## (Intercept) . . . .
## state -1.202337e-05 -1.315491e-05 -1.438886e-05 -1.573371e-05
## fold -1.023703e-05 -1.116936e-05 -1.218066e-05 -1.327663e-05
## population 2.586656e-03 2.819076e-03 3.070466e-03 3.342023e-03
## householdsize -2.051049e-04 -2.250070e-04 -2.468196e-04 -2.707196e-04
## racepctblack 2.260312e-03 2.467078e-03 2.691490e-03 2.934828e-03
## racePctWhite -2.524669e-03 -2.753368e-03 -3.001141e-03 -3.269285e-03
## racePctAsian 1.788685e-04 1.966214e-04 2.161212e-04 2.375285e-04
## racePctHisp 1.094379e-03 1.189420e-03 1.291586e-03 1.401202e-03
## agePct12t21 2.786086e-04 2.966228e-04 3.147654e-04 3.327850e-04
## agePct12t29 8.726983e-04 9.427835e-04 1.016986e-03 1.095254e-03
## agePct16t24 4.679561e-04 5.033835e-04 5.404299e-04 5.789491e-04
## agePct65up 3.316334e-04 3.611270e-04 3.929796e-04 4.273334e-04
## numbUrban 2.538654e-03 2.767680e-03 3.015578e-03 3.283576e-03
## pctUrban 1.915572e-04 2.114777e-04 2.335476e-04 2.580054e-04
## medIncome -1.732618e-03 -1.880492e-03 -2.038971e-03 -2.208449e-03
## pctWWage -1.457193e-03 -1.584640e-03 -1.721852e-03 -1.869330e-03
## pctWFarmSelf -6.958750e-04 -7.609645e-04 -8.318638e-04 -9.090381e-04
## pctWInvInc -2.836703e-03 -3.086135e-03 -3.354941e-03 -3.644170e-03
## pctWSocSec 5.850836e-04 6.354949e-04 6.896277e-04 7.476466e-04
## pctWPubAsst 2.270655e-03 2.470611e-03 2.686146e-03 2.918115e-03
## pctWRetire -5.190224e-04 -5.650488e-04 -6.147198e-04 -6.682452e-04
## medFamInc -1.899091e-03 -2.061752e-03 -2.236201e-03 -2.422907e-03
## perCapInc -1.557382e-03 -1.688449e-03 -1.828551e-03 -1.977947e-03
## whitePerCap -9.017482e-04 -9.728273e-04 -1.047826e-03 -1.126633e-03
## blackPerCap -1.371204e-03 -1.488186e-03 -1.613564e-03 -1.747656e-03
## indianPerCap -4.593433e-04 -4.973124e-04 -5.377650e-04 -5.807438e-04
## AsianPerCap -6.538426e-04 -7.067839e-04 -7.629412e-04 -8.223050e-04
## OtherPerCap -5.351832e-04 -5.777050e-04 -6.226376e-04 -6.699289e-04
## HispPerCap -1.112695e-03 -1.204550e-03 -1.302364e-03 -1.406221e-03
## NumUnderPov 3.113491e-03 3.391920e-03 3.692843e-03 4.017640e-03
## PctPopUnderPov 1.985574e-03 2.158468e-03 2.344457e-03 2.544181e-03
## PctLess9thGrade 1.662058e-03 1.805431e-03 1.959391e-03 2.124399e-03
## PctNotHSGrad 2.076419e-03 2.257404e-03 2.452134e-03 2.661293e-03
## PctBSorMore -1.289421e-03 -1.399869e-03 -1.518331e-03 -1.645130e-03
## PctUnemployed 2.173792e-03 2.363661e-03 2.568022e-03 2.787609e-03
## PctEmploy -1.647709e-03 -1.790312e-03 -1.943549e-03 -2.107910e-03
## PctEmplManu -2.189077e-04 -2.406523e-04 -2.645711e-04 -2.908794e-04
## PctEmplProfServ -3.583946e-04 -3.900512e-04 -4.241960e-04 -4.609703e-04
## PctOccupManu 1.265927e-03 1.373542e-03 1.488801e-03 1.611975e-03
## PctOccupMgmtProf -1.554670e-03 -1.687229e-03 -1.829282e-03 -1.981183e-03
## MalePctDivorce 2.566496e-03 2.796579e-03 3.045400e-03 3.314152e-03
## MalePctNevMarr 1.528529e-03 1.663539e-03 1.809134e-03 1.965900e-03
## FemalePctDiv 2.825333e-03 3.078200e-03 3.351572e-03 3.646735e-03
## TotalPctDiv 2.681080e-03 2.921195e-03 3.180815e-03 3.461173e-03
## PersPerFam 8.003619e-04 8.710222e-04 9.472232e-04 1.029275e-03
## PctFam2Par -3.109734e-03 -3.387658e-03 -3.688055e-03 -4.012324e-03
## PctKids2Par -3.185282e-03 -3.470451e-03 -3.778776e-03 -4.111719e-03
## PctYoungKids2Par -2.701599e-03 -2.942596e-03 -3.202997e-03 -3.483997e-03
## PctTeen2Par -3.079563e-03 -3.355709e-03 -3.654361e-03 -3.976954e-03
## PctWorkMomYoungKids -1.192706e-04 -1.299068e-04 -1.413835e-04 -1.537450e-04
## PctWorkMom -7.642329e-04 -8.325355e-04 -9.063486e-04 -9.860095e-04
## NumIlleg 3.884336e-03 4.234493e-03 4.613494e-03 5.023223e-03
## PctIlleg 2.879449e-03 3.139557e-03 3.421234e-03 3.725931e-03
## NumImmig 2.990532e-03 3.256431e-03 3.543467e-03 3.852857e-03
## PctImmigRecent 6.744575e-04 7.323488e-04 7.944466e-04 8.609161e-04
## PctImmigRec5 8.846867e-04 9.610560e-04 1.043062e-03 1.130946e-03
## PctImmigRec8 1.072878e-03 1.166471e-03 1.267170e-03 1.375323e-03
## PctImmigRec10 1.308828e-03 1.423655e-03 1.547333e-03 1.680322e-03
## PctRecentImmig 8.633642e-04 9.396970e-04 1.022008e-03 1.110620e-03
## PctRecImmig5 9.278368e-04 1.010087e-03 1.098823e-03 1.194408e-03
## PctRecImmig8 9.489573e-04 1.033441e-03 1.124660e-03 1.223004e-03
## PctRecImmig10 9.993591e-04 1.088427e-03 1.184617e-03 1.288346e-03
## PctSpeakEnglOnly -9.287983e-04 -1.009919e-03 -1.097204e-03 -1.190954e-03
## PctNotSpeakEnglWell 1.188255e-03 1.291732e-03 1.403021e-03 1.522493e-03
## PctLargHouseFam 1.719945e-03 1.872176e-03 2.036417e-03 2.213354e-03
## PctLargHouseOccup 1.358764e-03 1.478608e-03 1.607827e-03 1.746938e-03
## PersPerOccupHous -2.040185e-04 -2.218047e-04 -2.409396e-04 -2.614885e-04
## PersPerOwnOccHous -7.015359e-04 -7.643930e-04 -8.323680e-04 -9.057875e-04
## PersPerRentOccHous 1.151494e-03 1.252922e-03 1.362263e-03 1.479954e-03
## PctPersOwnOccup -2.332819e-03 -2.537460e-03 -2.757886e-03 -2.994926e-03
## PctPersDenseHous 1.897994e-03 2.065582e-03 2.246310e-03 2.440911e-03
## PctHousLess3BR 2.405878e-03 2.616843e-03 2.844059e-03 3.088374e-03
## MedNumBR -1.218949e-03 -1.325189e-03 -1.439483e-03 -1.562221e-03
## HousVacant 2.518240e-03 2.746113e-03 2.992925e-03 3.259948e-03
## PctHousOccup -1.468092e-03 -1.600025e-03 -1.742775e-03 -1.897047e-03
## PctHousOwnOcc -2.217839e-03 -2.411783e-03 -2.620561e-03 -2.844926e-03
## PctVacantBoarded 1.982837e-03 2.161315e-03 2.354472e-03 2.563273e-03
## PctVacMore6Mos 8.343711e-05 8.927247e-05 9.528115e-05 1.014197e-04
## MedYrHousBuilt -4.075328e-04 -4.425864e-04 -4.802001e-04 -5.204762e-04
## PctHousNoPhone 1.756215e-03 1.910101e-03 2.075847e-03 2.254081e-03
## PctWOFullPlumb 1.539195e-03 1.673575e-03 1.818200e-03 1.973584e-03
## OwnOccLowQuart -7.837473e-04 -8.488290e-04 -9.182416e-04 -9.920805e-04
## OwnOccMedVal -6.817269e-04 -7.376564e-04 -7.971689e-04 -8.603111e-04
## OwnOccHiQuart -5.985238e-04 -6.468724e-04 -6.981620e-04 -7.523933e-04
## RentLowQ -9.698824e-04 -1.051532e-03 -1.138838e-03 -1.231975e-03
## RentMedian -9.596127e-04 -1.039216e-03 -1.124092e-03 -1.214345e-03
## RentHighQ -7.787719e-04 -8.431081e-04 -9.116500e-04 -9.844704e-04
## MedRent -9.334982e-04 -1.010366e-03 -1.092201e-03 -1.179075e-03
## MedRentPctHousInc 1.700557e-03 1.852071e-03 2.015729e-03 2.192263e-03
## MedOwnCostPctInc 3.385094e-04 3.722299e-04 4.093174e-04 4.500985e-04
## MedOwnCostPctIncNoMtg 2.450682e-04 2.666230e-04 2.898448e-04 3.148199e-04
## NumInShelters 3.281311e-03 3.577007e-03 3.897030e-03 4.242959e-03
## NumStreet 3.051924e-03 3.328516e-03 3.628173e-03 3.952457e-03
## PctForeignBorn 7.534536e-04 8.212396e-04 8.945608e-04 9.737631e-04
## PctBornSameState -3.630007e-04 -3.981183e-04 -4.365703e-04 -4.786547e-04
## PctSameHouse85 -7.342925e-04 -7.970961e-04 -8.644224e-04 -9.364413e-04
## PctSameCity85 3.515587e-04 3.847104e-04 4.208851e-04 4.603404e-04
## PctSameState85 -9.171035e-05 -1.003021e-04 -1.096531e-04 -1.198198e-04
## LandArea 1.619201e-03 1.765939e-03 1.924905e-03 2.096924e-03
## PopDens 1.233233e-03 1.343477e-03 1.462609e-03 1.591167e-03
## PctUsePubTrans 6.246469e-04 6.831683e-04 7.469158e-04 8.163037e-04
##
## (Intercept) 2.458796e-01 2.465226e-01 2.472068e-01 2.479331e-01
## (Intercept) . . . .
## state -1.720086e-05 -1.879597e-05 -2.053106e-05 -2.241701e-05
## fold -1.447101e-05 -1.575664e-05 -1.714615e-05 -1.864640e-05
## population 3.636433e-03 3.952367e-03 4.292185e-03 4.657071e-03
## householdsize -2.967233e-04 -3.253337e-04 -3.566352e-04 -3.908608e-04
## racepctblack 3.199640e-03 3.485242e-03 3.794035e-03 4.127525e-03
## racePctWhite -3.560567e-03 -3.873900e-03 -4.211811e-03 -4.575730e-03
## racePctAsian 2.607053e-04 2.863698e-04 3.144658e-04 3.451877e-04
## racePctHisp 1.519581e-03 1.645254e-03 1.779250e-03 1.921755e-03
## agePct12t21 3.514859e-04 3.685679e-04 3.844598e-04 3.986366e-04
## agePct12t29 1.178850e-03 1.265176e-03 1.355025e-03 1.448001e-03
## agePct16t24 6.196422e-04 6.606793e-04 7.024327e-04 7.444822e-04
## agePct65up 4.648286e-04 5.047537e-04 5.476428e-04 5.936405e-04
## numbUrban 3.573882e-03 3.886097e-03 4.222236e-03 4.583545e-03
## pctUrban 2.848506e-04 3.148329e-04 3.480644e-04 3.848963e-04
## medIncome -2.391278e-03 -2.584258e-03 -2.789173e-03 -3.006135e-03
## pctWWage -2.028900e-03 -2.198705e-03 -2.380230e-03 -2.573868e-03
## pctWFarmSelf -9.930816e-04 -1.084339e-03 -1.183434e-03 -1.290940e-03
## pctWInvInc -3.957017e-03 -4.290728e-03 -4.647958e-03 -5.029598e-03
## pctWSocSec 8.103480e-04 8.767545e-04 9.474945e-04 1.022667e-03
## pctWPubAsst 3.168867e-03 3.436586e-03 3.723239e-03 4.029545e-03
## pctWRetire -7.260578e-04 -7.879734e-04 -8.543664e-04 -9.254248e-04
## medFamInc -2.623850e-03 -2.836661e-03 -3.062848e-03 -3.302589e-03
## perCapInc -2.138181e-03 -2.307029e-03 -2.485588e-03 -2.673787e-03
## whitePerCap -1.210087e-03 -1.296116e-03 -1.385152e-03 -1.476697e-03
## blackPerCap -1.891637e-03 -2.044171e-03 -2.206141e-03 -2.377642e-03
## indianPerCap -6.266338e-04 -6.747883e-04 -7.254584e-04 -7.785677e-04
## AsianPerCap -8.853780e-04 -9.510757e-04 -1.019668e-03 -1.090907e-03
## OtherPerCap -7.199875e-04 -7.717810e-04 -8.255006e-04 -8.808657e-04
## HispPerCap -1.516934e-03 -1.633066e-03 -1.755106e-03 -1.882812e-03
## NumUnderPov 4.368697e-03 4.745663e-03 5.150687e-03 5.585086e-03
## PctPopUnderPov 2.759112e-03 2.988312e-03 3.232975e-03 3.493541e-03
## PctLess9thGrade 2.301659e-03 2.490174e-03 2.690874e-03 2.903990e-03
## PctNotHSGrad 2.886302e-03 3.126422e-03 3.382819e-03 3.655972e-03
## PctBSorMore -1.781015e-03 -1.925418e-03 -2.078899e-03 -2.241582e-03
## PctUnemployed 3.023750e-03 3.276001e-03 3.545468e-03 3.832674e-03
## PctEmploy -2.284217e-03 -2.472227e-03 -2.672595e-03 -2.885602e-03
## PctEmplManu -3.197854e-04 -3.515941e-04 -3.865619e-04 -4.249913e-04
## PctEmplProfServ -5.006680e-04 -5.431594e-04 -5.886990e-04 -6.374133e-04
## PctOccupManu 1.743618e-03 1.883333e-03 2.031498e-03 2.188151e-03
## PctOccupMgmtProf -2.143554e-03 -2.316076e-03 -2.499181e-03 -2.692947e-03
## MalePctDivorce 3.604566e-03 3.916950e-03 4.252943e-03 4.613753e-03
## MalePctNevMarr 2.134862e-03 2.315793e-03 2.509579e-03 2.716704e-03
## FemalePctDiv 3.965496e-03 4.308269e-03 4.676759e-03 5.072241e-03
## TotalPctDiv 3.763870e-03 4.089532e-03 4.439695e-03 4.815590e-03
## PersPerFam 1.117657e-03 1.212364e-03 1.313818e-03 1.422287e-03
## PctFam2Par -4.362228e-03 -4.738565e-03 -5.143029e-03 -5.577000e-03
## PctKids2Par -4.471019e-03 -4.857706e-03 -5.273480e-03 -5.719808e-03
## PctYoungKids2Par -3.786927e-03 -4.112752e-03 -4.462775e-03 -4.838155e-03
## PctTeen2Par -4.325074e-03 -4.699955e-03 -5.103177e-03 -5.536194e-03
## PctWorkMomYoungKids -1.671645e-04 -1.814555e-04 -1.967536e-04 -2.130864e-04
## PctWorkMom -1.072002e-03 -1.164411e-03 -1.263681e-03 -1.370135e-03
## NumIlleg 5.465859e-03 5.942887e-03 6.456464e-03 7.008517e-03
## PctIlleg 4.055228e-03 4.410478e-03 4.793306e-03 5.205266e-03
## NumImmig 4.186231e-03 4.543999e-03 4.927611e-03 5.338087e-03
## PctImmigRecent 9.320664e-04 1.007726e-03 1.088111e-03 1.173266e-03
## PctImmigRec5 1.225087e-03 1.325387e-03 1.432124e-03 1.545397e-03
## PctImmigRec8 1.491404e-03 1.615453e-03 1.747855e-03 1.888829e-03
## PctImmigRec10 1.823196e-03 1.976145e-03 2.139657e-03 2.314072e-03
## PctRecentImmig 1.206060e-03 1.308260e-03 1.417664e-03 1.534515e-03
## PctRecImmig5 1.297372e-03 1.407750e-03 1.525999e-03 1.652409e-03
## PctRecImmig8 1.329004e-03 1.442787e-03 1.564824e-03 1.695450e-03
## PctRecImmig10 1.400144e-03 1.520217e-03 1.649045e-03 1.786991e-03
## PctSpeakEnglOnly -1.291527e-03 -1.399036e-03 -1.513766e-03 -1.635894e-03
## PctNotSpeakEnglWell 1.650536e-03 1.787380e-03 1.933327e-03 2.088589e-03
## PctLargHouseFam 2.403660e-03 2.607999e-03 2.827005e-03 3.061275e-03
## PctLargHouseOccup 1.896426e-03 2.056820e-03 2.228572e-03 2.412111e-03
## PersPerOccupHous -2.835241e-04 -3.070780e-04 -3.322090e-04 -3.589545e-04
## PersPerOwnOccHous -9.849714e-04 -1.070270e-03 -1.162012e-03 -1.260528e-03
## PersPerRentOccHous 1.606398e-03 1.742046e-03 1.887276e-03 2.042450e-03
## PctPersOwnOccup -3.249337e-03 -3.521937e-03 -3.813401e-03 -4.124347e-03
## PctPersDenseHous 2.650069e-03 2.874536e-03 3.114951e-03 3.371924e-03
## PctHousLess3BR 3.350543e-03 3.631431e-03 3.931706e-03 4.251990e-03
## MedNumBR -1.693735e-03 -1.834424e-03 -1.984559e-03 -2.144385e-03
## HousVacant 3.548442e-03 3.859796e-03 4.195322e-03 4.556355e-03
## PctHousOccup -2.063511e-03 -2.242979e-03 -2.436152e-03 -2.643765e-03
## PctHousOwnOcc -3.085499e-03 -3.343107e-03 -3.618288e-03 -3.911562e-03
## PctVacantBoarded 2.788634e-03 3.031667e-03 3.293333e-03 3.574637e-03
## PctVacMore6Mos 1.075945e-04 1.137981e-04 1.199207e-04 1.258627e-04
## MedYrHousBuilt -5.634821e-04 -6.093274e-04 -6.580479e-04 -7.096695e-04
## PctHousNoPhone 2.445303e-03 2.650275e-03 2.869462e-03 3.103354e-03
## PctWOFullPlumb 2.140139e-03 2.318455e-03 2.508887e-03 2.711792e-03
## OwnOccLowQuart -1.070290e-03 -1.153072e-03 -1.240309e-03 -1.331903e-03
## OwnOccMedVal -9.269847e-04 -9.973318e-04 -1.071187e-03 -1.148405e-03
## OwnOccHiQuart -8.094279e-04 -8.693462e-04 -9.319371e-04 -9.970016e-04
## RentLowQ -1.330969e-03 -1.436100e-03 -1.547326e-03 -1.664628e-03
## RentMedian -1.309927e-03 -1.411026e-03 -1.517497e-03 -1.629202e-03
## RentHighQ -1.061520e-03 -1.142919e-03 -1.228535e-03 -1.318230e-03
## MedRent -1.270925e-03 -1.367845e-03 -1.469660e-03 -1.576172e-03
## MedRentPctHousInc 2.382353e-03 2.586808e-03 2.806297e-03 3.041500e-03
## MedOwnCostPctInc 4.949468e-04 5.442112e-04 5.983173e-04 6.577042e-04
## MedOwnCostPctIncNoMtg 3.416233e-04 3.703431e-04 4.010419e-04 4.337763e-04
## NumInShelters 4.616334e-03 5.018890e-03 5.452193e-03 5.917838e-03
## NumStreet 4.302915e-03 4.681275e-03 5.089148e-03 5.528192e-03
## PctForeignBorn 1.059186e-03 1.151186e-03 1.250093e-03 1.356229e-03
## PctBornSameState -5.247047e-04 -5.750405e-04 -6.300360e-04 -6.900768e-04
## PctSameHouse85 -1.013268e-03 -1.095067e-03 -1.181895e-03 -1.273780e-03
## PctSameCity85 5.033465e-04 5.502105e-04 6.012451e-04 6.567892e-04
## PctSameState85 -1.308678e-04 -1.428445e-04 -1.558152e-04 -1.698393e-04
## LandArea 2.282813e-03 2.483476e-03 2.699761e-03 2.932531e-03
## PopDens 1.729666e-03 1.878676e-03 2.038697e-03 2.210219e-03
## PctUsePubTrans 8.917765e-04 9.737789e-04 1.062794e-03 1.159315e-03
##
## (Intercept) 2.487018e-01 2.495131e-01 2.503669e-01 2.512626e-01
## (Intercept) . . . .
## state -2.446522e-05 -2.668772e-05 -2.909708e-05 -3.170640e-05
## fold -2.026451e-05 -2.200787e-05 -2.388417e-05 -2.590137e-05
## population 5.048160e-03 5.466511e-03 5.913091e-03 6.388740e-03
## householdsize -4.282577e-04 -4.690864e-04 -5.136195e-04 -5.621391e-04
## racepctblack 4.487262e-03 4.874834e-03 5.291855e-03 5.739963e-03
## racePctWhite -4.967097e-03 -5.387343e-03 -5.837883e-03 -6.320101e-03
## racePctAsian 3.787347e-04 4.153078e-04 4.551061e-04 4.983222e-04
## racePctHisp 2.072896e-03 2.232722e-03 2.401194e-03 2.578173e-03
## agePct12t21 4.104817e-04 4.192781e-04 4.242010e-04 4.243112e-04
## agePct12t29 1.543576e-03 1.641082e-03 1.739691e-03 1.838400e-03
## agePct16t24 7.863114e-04 8.272966e-04 8.666962e-04 9.036405e-04
## agePct65up 6.428870e-04 6.955158e-04 7.516516e-04 8.114079e-04
## numbUrban 4.971234e-03 5.386454e-03 5.830276e-03 6.303662e-03
## pctUrban 4.257136e-04 4.709367e-04 5.210236e-04 5.764703e-04
## medIncome -3.235141e-03 -3.476051e-03 -3.728572e-03 -3.992239e-03
## pctWWage -2.779955e-03 -2.998759e-03 -3.230464e-03 -3.475161e-03
## pctWFarmSelf -1.407450e-03 -1.533577e-03 -1.669954e-03 -1.817220e-03
## pctWInvInc -5.436443e-03 -5.869176e-03 -6.328345e-03 -6.814339e-03
## pctWSocSec 1.102344e-03 1.186561e-03 1.275317e-03 1.368566e-03
## pctWPubAsst 4.356150e-03 4.703605e-03 5.072348e-03 5.462681e-03
## pctWRetire -1.001322e-03 -1.082213e-03 -1.168232e-03 -1.259483e-03
## medFamInc -3.555940e-03 -3.822819e-03 -4.102983e-03 -4.396012e-03
## perCapInc -2.871425e-03 -3.078156e-03 -3.293469e-03 -3.516676e-03
## whitePerCap -1.570111e-03 -1.664606e-03 -1.759226e-03 -1.852831e-03
## blackPerCap -2.558685e-03 -2.749176e-03 -2.948910e-03 -3.157551e-03
## indianPerCap -8.339965e-04 -8.915769e-04 -9.510881e-04 -1.012252e-03
## AsianPerCap -1.164460e-03 -1.239898e-03 -1.316680e-03 -1.394151e-03
## OtherPerCap -9.375141e-04 -9.949921e-04 -1.052744e-03 -1.110103e-03
## HispPerCap -2.015822e-03 -2.153636e-03 -2.295604e-03 -2.440905e-03
## NumUnderPov 6.050108e-03 6.546904e-03 7.076500e-03 7.639765e-03
## PctPopUnderPov 3.770355e-03 4.063651e-03 4.373535e-03 4.699963e-03
## PctLess9thGrade 3.129650e-03 3.367872e-03 3.618538e-03 3.881379e-03
## PctNotHSGrad 3.946269e-03 4.253985e-03 4.579264e-03 4.922100e-03
## PctBSorMore -2.413511e-03 -2.594635e-03 -2.784801e-03 -2.983737e-03
## PctUnemployed 4.138047e-03 4.461901e-03 4.804408e-03 5.165585e-03
## PctEmploy -3.111446e-03 -3.350219e-03 -3.601895e-03 -3.866312e-03
## PctEmplManu -4.672088e-04 -5.135666e-04 -5.644425e-04 -6.202402e-04
## PctEmplProfServ -6.894195e-04 -7.448227e-04 -8.037139e-04 -8.661667e-04
## PctOccupManu 2.353240e-03 2.526610e-03 2.707986e-03 2.896966e-03
## PctOccupMgmtProf -2.897349e-03 -3.112240e-03 -3.337328e-03 -3.572171e-03
## MalePctDivorce 5.000558e-03 5.414491e-03 5.856625e-03 6.327948e-03
## MalePctNevMarr 2.937601e-03 3.172631e-03 3.422069e-03 3.686093e-03
## FemalePctDiv 5.495946e-03 5.949045e-03 6.432624e-03 6.947669e-03
## TotalPctDiv 5.218410e-03 5.649294e-03 6.109309e-03 6.599428e-03
## PersPerFam 1.538014e-03 1.661209e-03 1.792051e-03 1.930674e-03
## PctFam2Par -6.041815e-03 -6.538742e-03 -7.068962e-03 -7.633547e-03
## PctKids2Par -6.198117e-03 -6.709775e-03 -7.256071e-03 -7.838194e-03
## PctYoungKids2Par -5.240011e-03 -5.669397e-03 -6.127289e-03 -6.614564e-03
## PctTeen2Par -6.000422e-03 -6.497226e-03 -7.027897e-03 -7.593632e-03
## PctWorkMomYoungKids -2.304722e-04 -2.489181e-04 -2.684166e-04 -2.889432e-04
## PctWorkMom -1.484074e-03 -1.605781e-03 -1.735505e-03 -1.873462e-03
## NumIlleg 7.600931e-03 8.235516e-03 8.913980e-03 9.637893e-03
## PctIlleg 5.647911e-03 6.122778e-03 6.631373e-03 7.175153e-03
## NumImmig 5.776334e-03 6.243108e-03 6.738979e-03 7.264289e-03
## PctImmigRecent 1.263185e-03 1.357804e-03 1.456992e-03 1.560543e-03
## PctImmigRec5 1.665249e-03 1.791650e-03 1.924491e-03 2.063569e-03
## PctImmigRec8 2.038539e-03 2.197078e-03 2.364460e-03 2.540603e-03
## PctImmigRec10 2.499667e-03 2.696652e-03 2.905147e-03 3.125177e-03
## PctRecentImmig 1.659020e-03 1.791330e-03 1.931534e-03 2.079648e-03
## PctRecImmig5 1.787230e-03 1.930662e-03 2.082840e-03 2.243830e-03
## PctRecImmig8 1.834962e-03 1.983614e-03 2.141603e-03 2.309056e-03
## PctRecImmig10 1.934385e-03 2.091512e-03 2.258600e-03 2.435808e-03
## PctSpeakEnglOnly -1.765540e-03 -1.902761e-03 -2.047531e-03 -2.199734e-03
## PctNotSpeakEnglWell 2.253303e-03 2.427524e-03 2.611206e-03 2.804187e-03
## PctLargHouseFam 3.311351e-03 3.577712e-03 3.860752e-03 4.160774e-03
## PctLargHouseOccup 2.607820e-03 2.816024e-03 3.036981e-03 3.270863e-03
## PersPerOccupHous -3.873390e-04 -4.173709e-04 -4.490393e-04 -4.823102e-04
## PersPerOwnOccHous -1.366141e-03 -1.479162e-03 -1.599885e-03 -1.728581e-03
## PersPerRentOccHous 2.207896e-03 2.383891e-03 2.570661e-03 2.768364e-03
## PctPersOwnOccup -4.455298e-03 -4.806653e-03 -5.178666e-03 -5.571425e-03
## PctPersDenseHous 3.646002e-03 3.937650e-03 4.247234e-03 4.575005e-03
## PctHousLess3BR 4.592801e-03 4.954526e-03 5.337398e-03 5.741471e-03
## MedNumBR -2.314083e-03 -2.493754e-03 -2.683410e-03 -2.882952e-03
## HousVacant 4.944215e-03 5.360189e-03 5.805514e-03 6.281354e-03
## PctHousOccup -2.866546e-03 -3.105206e-03 -3.360434e-03 -3.632887e-03
## PctHousOwnOcc -4.223344e-03 -4.553923e-03 -4.903434e-03 -5.271839e-03
## PctVacantBoarded 3.876577e-03 4.200128e-03 4.546230e-03 4.915780e-03
## PctVacMore6Mos 1.315074e-04 1.367197e-04 1.413453e-04 1.452101e-04
## MedYrHousBuilt -7.641863e-04 -8.215549e-04 -8.816878e-04 -9.444464e-04
## PctHousNoPhone 3.352380e-03 3.616890e-03 3.897141e-03 4.193285e-03
## PctWOFullPlumb 2.927452e-03 3.156068e-03 3.397736e-03 3.652437e-03
## OwnOccLowQuart -1.427693e-03 -1.527440e-03 -1.630823e-03 -1.737435e-03
## OwnOccMedVal -1.228771e-03 -1.312000e-03 -1.397722e-03 -1.485484e-03
## OwnOccHiQuart -1.064273e-03 -1.133409e-03 -1.203987e-03 -1.275497e-03
## RentLowQ -1.787910e-03 -1.917001e-03 -2.051639e-03 -2.191463e-03
## RentMedian -1.745913e-03 -1.867303e-03 -1.992941e-03 -2.122272e-03
## RentHighQ -1.411791e-03 -1.508922e-03 -1.609236e-03 -1.712244e-03
## MedRent -1.687088e-03 -1.802007e-03 -1.920412e-03 -2.041655e-03
## MedRentPctHousInc 3.293055e-03 3.561548e-03 3.847495e-03 4.151331e-03
## MedOwnCostPctInc 7.228388e-04 7.942141e-04 8.723465e-04 9.577721e-04
## MedOwnCostPctIncNoMtg 4.685888e-04 5.055033e-04 5.445220e-04 5.856200e-04
## NumInShelters 6.417373e-03 6.952275e-03 7.523922e-03 8.133562e-03
## NumStreet 6.000048e-03 6.506325e-03 7.048575e-03 7.628269e-03
## PctForeignBorn 1.469893e-03 1.591356e-03 1.720846e-03 1.858547e-03
## PctBornSameState -7.555692e-04 -8.269383e-04 -9.046257e-04 -9.890863e-04
## PctSameHouse85 -1.370697e-03 -1.472557e-03 -1.579197e-03 -1.690368e-03
## PctSameCity85 7.172040e-04 7.828742e-04 8.542078e-04 9.316370e-04
## PctSameState85 -1.849747e-04 -2.012759e-04 -2.187929e-04 -2.375689e-04
## LandArea 3.182639e-03 3.450911e-03 3.738139e-03 4.045058e-03
## PopDens 2.393699e-03 2.589546e-03 2.798108e-03 3.019658e-03
## PctUsePubTrans 1.263850e-03 1.376915e-03 1.499032e-03 1.630718e-03
##
## (Intercept) 2.521990e-01 2.531746e-01 2.541875e-01 2.552350e-01
## (Intercept) . . . .
## state -3.452930e-05 -3.757982e-05 -4.087244e-05 -4.442194e-05
## fold -2.806779e-05 -3.039210e-05 -3.288339e-05 -3.555127e-05
## population 6.894142e-03 7.429799e-03 7.995990e-03 8.592743e-03
## householdsize -6.149338e-04 -6.722942e-04 -7.345075e-04 -8.018500e-04
## racepctblack 6.220811e-03 6.736057e-03 7.287356e-03 7.876353e-03
## racePctWhite -6.835334e-03 -7.384856e-03 -7.969869e-03 -8.591483e-03
## racePctAsian 5.451361e-04 5.957086e-04 6.501731e-04 7.086272e-04
## racePctHisp 2.763400e-03 2.956493e-03 3.156925e-03 3.364020e-03
## agePct12t21 4.185511e-04 4.057415e-04 3.845826e-04 3.536575e-04
## agePct12t29 1.936016e-03 2.031143e-03 2.122172e-03 2.207275e-03
## agePct16t24 9.371227e-04 9.659919e-04 9.889478e-04 1.004539e-03
## agePct65up 8.748842e-04 9.421636e-04 1.013309e-03 1.088360e-03
## numbUrban 6.807439e-03 7.342267e-03 7.908606e-03 8.506683e-03
## pctUrban 6.378120e-04 7.056232e-04 7.805167e-04 8.631431e-04
## medIncome -4.266395e-03 -4.550180e-03 -4.842512e-03 -5.142080e-03
## pctWWage -3.732836e-03 -4.003351e-03 -4.286441e-03 -4.581699e-03
## pctWFarmSelf -1.976026e-03 -2.147019e-03 -2.330839e-03 -2.528106e-03
## pctWInvInc -7.327366e-03 -7.867434e-03 -8.434332e-03 -9.027615e-03
## pctWSocSec 1.466215e-03 1.568118e-03 1.674073e-03 1.783817e-03
## pctWPubAsst 5.874757e-03 6.308555e-03 6.763863e-03 7.240263e-03
## pctWRetire -1.356044e-03 -1.457956e-03 -1.565227e-03 -1.677825e-03
## medFamInc -4.701286e-03 -5.017974e-03 -5.345013e-03 -5.681106e-03
## perCapInc -3.746888e-03 -3.983007e-03 -4.223717e-03 -4.467472e-03
## whitePerCap -1.944090e-03 -2.031470e-03 -2.113227e-03 -2.187406e-03
## blackPerCap -3.374626e-03 -3.599515e-03 -3.831440e-03 -4.069469e-03
## indianPerCap -1.074729e-03 -1.138118e-03 -1.201954e-03 -1.265709e-03
## AsianPerCap -1.471523e-03 -1.547875e-03 -1.622136e-03 -1.693091e-03
## OtherPerCap -1.166282e-03 -1.220365e-03 -1.271299e-03 -1.317896e-03
## HispPerCap -2.588539e-03 -2.737307e-03 -2.885809e-03 -3.032430e-03
## NumUnderPov 8.237378e-03 8.869792e-03 9.537200e-03 1.023950e-02
## PctPopUnderPov 5.042724e-03 5.401422e-03 5.775461e-03 6.164034e-03
## PctLess9thGrade 4.155960e-03 4.441659e-03 4.737658e-03 5.042926e-03
## PctNotHSGrad 5.282320e-03 5.659564e-03 6.053273e-03 6.462674e-03
## PctBSorMore -3.191039e-03 -3.406166e-03 -3.628429e-03 -3.856985e-03
## PctUnemployed 5.545267e-03 5.943090e-03 6.358471e-03 6.790594e-03
## PctEmploy -4.143159e-03 -4.431958e-03 -4.732055e-03 -5.042606e-03
## PctEmplManu -6.813890e-04 -7.483432e-04 -8.215803e-04 -9.015999e-04
## PctEmplProfServ -9.322353e-04 -1.001952e-03 -1.075326e-03 -1.152339e-03
## PctOccupManu 3.093001e-03 3.295392e-03 3.503278e-03 3.715631e-03
## PctOccupMgmtProf -3.816151e-03 -4.068469e-03 -4.328132e-03 -4.593946e-03
## MalePctDivorce 6.829351e-03 7.361607e-03 7.925351e-03 8.521065e-03
## MalePctNevMarr 3.964760e-03 4.257999e-03 4.565590e-03 4.887151e-03
## FemalePctDiv 7.495036e-03 8.075433e-03 8.689397e-03 9.337269e-03
## TotalPctDiv 7.120512e-03 7.673287e-03 8.258326e-03 8.876026e-03
## PersPerFam 2.077164e-03 2.231557e-03 2.393832e-03 2.563911e-03
## PctFam2Par -8.233440e-03 -8.869428e-03 -9.542126e-03 -1.025195e-02
## PctKids2Par -8.457209e-03 -9.114040e-03 -9.809448e-03 -1.054401e-02
## PctYoungKids2Par -7.131981e-03 -7.680164e-03 -8.259586e-03 -8.870551e-03
## PctTeen2Par -8.195510e-03 -8.834476e-03 -9.511312e-03 -1.022663e-02
## PctWorkMomYoungKids -3.104523e-04 -3.328742e-04 -3.561108e-04 -3.800321e-04
## PctWorkMom -2.019823e-03 -2.174710e-03 -2.338187e-03 -2.510255e-03
## NumIlleg 1.040865e-02 1.122744e-02 1.209519e-02 1.301254e-02
## PctIlleg 7.755510e-03 8.373759e-03 9.031117e-03 9.728693e-03
## NumImmig 7.819112e-03 8.403202e-03 9.015953e-03 9.656349e-03
## PctImmigRecent 1.668165e-03 1.779471e-03 1.893975e-03 2.011084e-03
## PctImmigRec5 2.208577e-03 2.359095e-03 2.514575e-03 2.674336e-03
## PctImmigRec8 2.725321e-03 2.918306e-03 3.119122e-03 3.327192e-03
## PctImmigRec10 3.356649e-03 3.599344e-03 3.852905e-03 4.116821e-03
## PctRecentImmig 2.235598e-03 2.399209e-03 2.570193e-03 2.748134e-03
## PctRecImmig5 2.413606e-03 2.592042e-03 2.778901e-03 2.973814e-03
## PctRecImmig8 2.486021e-03 2.672449e-03 2.868185e-03 3.072953e-03
## PctRecImmig10 2.623214e-03 2.820801e-03 3.028445e-03 3.245898e-03
## PctSpeakEnglOnly -2.359147e-03 -2.525429e-03 -2.698105e-03 -2.876558e-03
## PctNotSpeakEnglWell 3.006172e-03 3.216721e-03 3.435230e-03 3.660918e-03
## PctLargHouseFam 4.477966e-03 4.812396e-03 5.163990e-03 5.532528e-03
## PctLargHouseOccup 3.517752e-03 3.777623e-03 4.050340e-03 4.335644e-03
## PersPerOccupHous -5.171215e-04 -5.533787e-04 -5.909492e-04 -6.296564e-04
## PersPerOwnOccHous -1.865496e-03 -2.010838e-03 -2.164781e-03 -2.327449e-03
## PersPerRentOccHous 2.977089e-03 3.196843e-03 3.427545e-03 3.669027e-03
## PctPersOwnOccup -5.984825e-03 -6.418545e-03 -6.872028e-03 -7.344465e-03
## PctPersDenseHous 4.921081e-03 5.285428e-03 5.667850e-03 6.067970e-03
## PctHousLess3BR 6.166592e-03 6.612380e-03 7.078197e-03 7.563131e-03
## MedNumBR -3.092165e-03 -3.310697e-03 -3.538046e-03 -3.773553e-03
## HousVacant 6.788777e-03 7.328736e-03 7.902037e-03 8.509324e-03
## PctHousOccup -3.923185e-03 -4.231897e-03 -4.559542e-03 -4.906575e-03
## PctHousOwnOcc -5.658900e-03 -6.064155e-03 -6.486898e-03 -6.926160e-03
## PctVacantBoarded 5.309618e-03 5.728512e-03 6.173150e-03 6.644130e-03
## PctVacMore6Mos 1.481199e-04 1.498609e-04 1.502008e-04 1.488895e-04
## MedYrHousBuilt -1.009634e-03 -1.076988e-03 -1.146175e-03 -1.216778e-03
## PctHousNoPhone 4.505356e-03 4.833255e-03 5.176745e-03 5.535438e-03
## PctWOFullPlumb 3.920018e-03 4.200182e-03 4.492469e-03 4.796253e-03
## OwnOccLowQuart -1.846773e-03 -1.958239e-03 -2.071142e-03 -2.184696e-03
## OwnOccMedVal -1.574741e-03 -1.664854e-03 -1.755092e-03 -1.844637e-03
## OwnOccHiQuart -1.347336e-03 -1.418811e-03 -1.489135e-03 -1.557434e-03
## RentLowQ -2.336014e-03 -2.484721e-03 -2.636908e-03 -2.791794e-03
## RentMedian -2.254620e-03 -2.389178e-03 -2.525004e-03 -2.661027e-03
## RentHighQ -1.817355e-03 -1.923863e-03 -2.030955e-03 -2.137703e-03
## MedRent -2.164954e-03 -2.289380e-03 -2.413859e-03 -2.537170e-03
## MedRentPctHousInc 4.473394e-03 4.813907e-03 5.172967e-03 5.550532e-03
## MedOwnCostPctInc 1.051041e-03 1.152713e-03 1.263343e-03 1.383481e-03
## MedOwnCostPctIncNoMtg 6.287401e-04 6.737875e-04 7.206228e-04 7.690558e-04
## NumInShelters 8.782278e-03 9.470956e-03 1.020025e-02 1.097052e-02
## NumStreet 8.246772e-03 8.905315e-03 9.604966e-03 1.034660e-02
## PctForeignBorn 2.004580e-03 2.158996e-03 2.321763e-03 2.492754e-03
## PctBornSameState -1.080784e-03 -1.180188e-03 -1.287762e-03 -1.403966e-03
## PctSameHouse85 -1.805733e-03 -1.924849e-03 -2.047169e-03 -2.172031e-03
## PctSameCity85 1.015618e-03 1.106631e-03 1.205180e-03 1.311791e-03
## PctSameState85 -2.576382e-04 -2.790238e-04 -3.017349e-04 -3.257640e-04
## LandArea 4.372337e-03 4.720556e-03 5.090188e-03 5.481579e-03
## PopDens 3.254379e-03 3.502350e-03 3.763526e-03 4.037724e-03
## PctUsePubTrans 1.772481e-03 1.924809e-03 2.088158e-03 2.262942e-03
##
## (Intercept) 2.563142e-01 2.574217e-01 2.585537e-01 2.597061e-01
## (Intercept) . . . .
## state -4.824339e-05 -5.235203e-05 -5.676320e-05 -6.149221e-05
## fold -3.840593e-05 -4.145829e-05 -4.472013e-05 -4.820430e-05
## population 9.219795e-03 9.876561e-03 1.056210e-02 1.127507e-02
## householdsize -8.745783e-04 -9.529183e-04 -1.037053e-03 -1.127107e-03
## racepctblack 8.504676e-03 9.173925e-03 9.885667e-03 1.064143e-02
## racePctWhite -9.250707e-03 -9.948437e-03 -1.068544e-02 -1.146237e-02
## racePctAsian 7.711225e-04 8.376540e-04 9.081493e-04 9.824575e-04
## racePctHisp 3.576942e-03 3.794686e-03 4.016082e-03 4.239788e-03
## agePct12t21 3.114406e-04 2.563096e-04 1.865630e-04 1.004426e-04
## agePct12t29 2.284400e-03 2.351275e-03 2.405420e-03 2.444152e-03
## agePct16t24 1.011162e-03 1.007073e-03 9.903912e-04 9.591180e-04
## agePct65up 1.167331e-03 1.250204e-03 1.336925e-03 1.427403e-03
## numbUrban 9.136459e-03 9.797593e-03 1.048941e-02 1.121085e-02
## pctUrban 9.541879e-04 1.054369e-03 1.164433e-03 1.285150e-03
## medIncome -5.447337e-03 -5.756500e-03 -6.067549e-03 -6.378238e-03
## pctWWage -4.888567e-03 -5.206334e-03 -5.534127e-03 -5.870915e-03
## pctWFarmSelf -2.739413e-03 -2.965312e-03 -3.206297e-03 -3.462797e-03
## pctWInvInc -9.646593e-03 -1.029032e-02 -1.095762e-02 -1.164703e-02
## pctWSocSec 1.897029e-03 2.013321e-03 2.132246e-03 2.253292e-03
## pctWPubAsst 7.737118e-03 8.253562e-03 8.788492e-03 9.340569e-03
## pctWRetire -1.795678e-03 -1.918681e-03 -2.046690e-03 -2.179535e-03
## medFamInc -6.024708e-03 -6.374031e-03 -6.727045e-03 -7.081492e-03
## perCapInc -4.712499e-03 -4.956801e-03 -5.198168e-03 -5.434195e-03
## whitePerCap -2.251846e-03 -2.304184e-03 -2.341877e-03 -2.362220e-03
## blackPerCap -4.312507e-03 -4.559308e-03 -4.808484e-03 -5.058519e-03
## indianPerCap -1.328797e-03 -1.390580e-03 -1.450376e-03 -1.507472e-03
## AsianPerCap -1.759371e-03 -1.819460e-03 -1.871697e-03 -1.914286e-03
## OtherPerCap -1.358822e-03 -1.392605e-03 -1.417636e-03 -1.432179e-03
## HispPerCap -3.175343e-03 -3.312510e-03 -3.441689e-03 -3.560452e-03
## NumUnderPov 1.097625e-02 1.174667e-02 1.254954e-02 1.338326e-02
## PctPopUnderPov 6.566110e-03 6.980433e-03 7.405519e-03 7.839666e-03
## PctLess9thGrade 5.356216e-03 5.676061e-03 6.000771e-03 6.328445e-03
## PctNotHSGrad 6.886772e-03 7.324348e-03 7.773960e-03 8.233952e-03
## PctBSorMore -4.090835e-03 -4.328828e-03 -4.569665e-03 -4.811912e-03
## PctUnemployed 7.238396e-03 7.700562e-03 8.175518e-03 8.661440e-03
## PctEmploy -5.362577e-03 -5.690738e-03 -6.025664e-03 -6.365748e-03
## PctEmplManu -9.889201e-04 -1.084075e-03 -1.187612e-03 -1.300083e-03
## PctEmplProfServ -1.232948e-03 -1.317081e-03 -1.404639e-03 -1.495497e-03
## PctOccupManu 3.931255e-03 4.148791e-03 4.366721e-03 4.583389e-03
## PctOccupMgmtProf -4.864513e-03 -5.138237e-03 -5.413332e-03 -5.687837e-03
## MalePctDivorce 9.149059e-03 9.809460e-03 1.050220e-02 1.122700e-02
## MalePctNevMarr 5.222131e-03 5.569796e-03 5.929230e-03 6.299330e-03
## FemalePctDiv 1.001918e-02 1.073502e-02 1.148445e-02 1.226686e-02
## TotalPctDiv 9.526594e-03 1.021003e-02 1.092611e-02 1.167439e-02
## PersPerFam 2.741660e-03 2.926886e-03 3.119349e-03 3.318764e-03
## PctFam2Par -1.099913e-02 -1.178365e-02 -1.260527e-02 -1.346354e-02
## PctKids2Par -1.131811e-02 -1.213194e-02 -1.298544e-02 -1.387839e-02
## PctYoungKids2Par -9.513187e-03 -1.018743e-02 -1.089304e-02 -1.162956e-02
## PctTeen2Par -1.098084e-02 -1.177415e-02 -1.260655e-02 -1.347781e-02
## PctWorkMomYoungKids -4.044716e-04 -4.292230e-04 -4.540365e-04 -4.786159e-04
## PctWorkMom -2.690849e-03 -2.879827e-03 -3.076979e-03 -3.282017e-03
## NumIlleg 1.397979e-02 1.499688e-02 1.606335e-02 1.717830e-02
## PctIlleg 1.046747e-02 1.124832e-02 1.207194e-02 1.293894e-02
## NumImmig 1.032292e-02 1.101368e-02 1.172612e-02 1.245714e-02
## PctImmigRecent 2.130090e-03 2.250174e-03 2.370404e-03 2.489737e-03
## PctImmigRec5 2.837559e-03 3.003279e-03 3.170386e-03 3.337630e-03
## PctImmigRec8 3.541791e-03 3.762041e-03 3.986908e-03 4.215206e-03
## PctImmigRec10 4.390422e-03 4.672871e-03 4.963167e-03 5.260139e-03
## PctRecentImmig 2.932477e-03 3.122521e-03 3.317407e-03 3.516115e-03
## PctRecImmig5 3.176279e-03 3.385640e-03 3.601088e-03 3.821648e-03
## PctRecImmig8 3.286346e-03 3.507812e-03 3.736652e-03 3.972007e-03
## PctRecImmig10 3.472783e-03 3.708575e-03 3.952603e-03 4.204034e-03
## PctSpeakEnglOnly -3.060014e-03 -3.247537e-03 -3.438023e-03 -3.630195e-03
## PctNotSpeakEnglWell 3.892818e-03 4.129768e-03 4.370404e-03 4.613166e-03
## PctLargHouseFam 5.917634e-03 6.318768e-03 6.735233e-03 7.166169e-03
## PctLargHouseOccup 4.633149e-03 4.942341e-03 5.262580e-03 5.593103e-03
## PersPerOccupHous -6.692731e-04 -7.095148e-04 -7.500320e-04 -7.904031e-04
## PersPerOwnOccHous -2.498919e-03 -2.679207e-03 -2.868269e-03 -3.065993e-03
## PersPerRentOccHous 3.921028e-03 4.183193e-03 4.455085e-03 4.736185e-03
## PctPersOwnOccup -7.834774e-03 -8.341598e-03 -8.863295e-03 -9.397945e-03
## PctPersDenseHous 6.485225e-03 6.918861e-03 7.367927e-03 7.831286e-03
## PctHousLess3BR 8.065981e-03 8.585239e-03 9.119091e-03 9.665414e-03
## MedNumBR -4.016388e-03 -4.265547e-03 -4.519843e-03 -4.777913e-03
## HousVacant 9.151045e-03 9.827437e-03 1.053850e-02 1.128396e-02
## PctHousOccup -5.273391e-03 -5.660313e-03 -6.067598e-03 -6.495436e-03
## PctHousOwnOcc -7.380690e-03 -7.848952e-03 -8.329111e-03 -8.819044e-03
## PctVacantBoarded 7.141946e-03 7.666984e-03 8.219517e-03 8.799703e-03
## PctVacMore6Mos 1.456617e-04 1.402394e-04 1.323345e-04 1.216526e-04
## MedYrHousBuilt -1.288295e-03 -1.360133e-03 -1.431596e-03 -1.501889e-03
## PctHousNoPhone 5.908798e-03 6.296134e-03 6.696612e-03 7.109257e-03
## PctWOFullPlumb 5.110725e-03 5.434893e-03 5.767580e-03 6.107427e-03
## OwnOccLowQuart -2.298029e-03 -2.410197e-03 -2.520194e-03 -2.626977e-03
## OwnOccMedVal -1.932584e-03 -2.017961e-03 -2.099735e-03 -2.176839e-03
## OwnOccHiQuart -1.622750e-03 -1.684055e-03 -1.740264e-03 -1.790256e-03
## RentLowQ -2.948494e-03 -3.106035e-03 -3.263371e-03 -3.419396e-03
## RentMedian -2.796047e-03 -2.928749e-03 -3.057718e-03 -3.181455e-03
## RentHighQ -2.243075e-03 -2.345939e-03 -2.445079e-03 -2.539209e-03
## MedRent -2.657947e-03 -2.774690e-03 -2.885777e-03 -2.989484e-03
## MedRentPctHousInc 5.946407e-03 6.360237e-03 6.791501e-03 7.239512e-03
## MedOwnCostPctInc 1.513650e-03 1.654338e-03 1.805982e-03 1.968951e-03
## MedOwnCostPctIncNoMtg 8.188369e-04 8.696499e-04 9.211023e-04 9.727159e-04
## NumInShelters 1.178186e-02 1.263398e-02 1.352624e-02 1.445759e-02
## NumStreet 1.113089e-02 1.195824e-02 1.282881e-02 1.374246e-02
## PctForeignBorn 2.671737e-03 2.858363e-03 3.052157e-03 3.252514e-03
## PctBornSameState -1.529236e-03 -1.663988e-03 -1.808597e-03 -1.963395e-03
## PctSameHouse85 -2.298655e-03 -2.426143e-03 -2.553484e-03 -2.679556e-03
## PctSameCity85 1.427009e-03 1.551400e-03 1.685542e-03 1.830026e-03
## PctSameState85 -3.510843e-04 -3.776470e-04 -4.053791e-04 -4.341812e-04
## LandArea 5.894931e-03 6.330274e-03 6.787453e-03 7.266103e-03
## PopDens 4.324607e-03 4.623675e-03 4.934242e-03 5.255438e-03
## PctUsePubTrans 2.449520e-03 2.648179e-03 2.859117e-03 3.082432e-03
##
## (Intercept) 2.608745e-01 2.620619e-01 2.632518e-01 2.644454e-01
## (Intercept) . . . .
## state -6.655428e-05 -7.195888e-05 -7.773107e-05 -8.388060e-05
## fold -5.192490e-05 -5.588670e-05 -6.013112e-05 -6.466699e-05
## population 1.201373e-02 1.277450e-02 1.355791e-02 1.435942e-02
## householdsize -1.223131e-03 -1.327394e-03 -1.435775e-03 -1.549780e-03
## racepctblack 1.144269e-02 1.229003e-02 1.318709e-02 1.413417e-02
## racePctWhite -1.227971e-02 -1.313733e-02 -1.403725e-02 -1.497878e-02
## racePctAsian 1.060338e-03 1.141685e-03 1.225333e-03 1.311042e-03
## racePctHisp 4.464299e-03 4.687311e-03 4.908774e-03 5.125998e-03
## agePct12t21 -3.838690e-06 -1.302403e-04 -2.760548e-04 -4.449385e-04
## agePct12t29 2.464620e-03 2.463154e-03 2.438691e-03 2.387147e-03
## agePct16t24 9.111589e-04 8.442488e-04 7.569434e-04 6.467077e-04
## agePct65up 1.521500e-03 1.618132e-03 1.719006e-03 1.822954e-03
## numbUrban 1.196049e-02 1.273786e-02 1.353882e-02 1.436144e-02
## pctUrban 1.417309e-03 1.562119e-03 1.719484e-03 1.890614e-03
## medIncome -6.686115e-03 -6.988933e-03 -7.284670e-03 -7.570069e-03
## pctWWage -6.215505e-03 -6.567475e-03 -6.924760e-03 -7.286013e-03
## pctWFarmSelf -3.735151e-03 -4.023972e-03 -4.328812e-03 -4.649908e-03
## pctWInvInc -1.235690e-02 -1.308771e-02 -1.383486e-02 -1.459728e-02
## pctWSocSec 2.375888e-03 2.500530e-03 2.625123e-03 2.749582e-03
## pctWPubAsst 9.908219e-03 1.049234e-02 1.108736e-02 1.169269e-02
## pctWRetire -2.317020e-03 -2.459215e-03 -2.605546e-03 -2.755985e-03
## medFamInc -7.434904e-03 -7.788458e-03 -8.133880e-03 -8.470707e-03
## perCapInc -5.662308e-03 -5.883669e-03 -6.089724e-03 -6.280179e-03
## whitePerCap -2.362377e-03 -2.342989e-03 -2.295590e-03 -2.219641e-03
## blackPerCap -5.307794e-03 -5.558224e-03 -5.802410e-03 -6.041126e-03
## indianPerCap -1.561139e-03 -1.612102e-03 -1.657378e-03 -1.697327e-03
## AsianPerCap -1.945314e-03 -1.964878e-03 -1.967574e-03 -1.952734e-03
## OtherPerCap -1.434380e-03 -1.424288e-03 -1.396714e-03 -1.350966e-03
## HispPerCap -3.666208e-03 -3.759609e-03 -3.832432e-03 -3.884180e-03
## NumUnderPov 1.424576e-02 1.513828e-02 1.605195e-02 1.698596e-02
## PctPopUnderPov 8.280964e-03 8.731509e-03 9.182277e-03 9.633874e-03
## PctLess9thGrade 6.656986e-03 6.987643e-03 7.312314e-03 7.630963e-03
## PctNotHSGrad 8.702467e-03 9.181719e-03 9.662560e-03 1.014577e-02
## PctBSorMore -5.054016e-03 -5.297584e-03 -5.535438e-03 -5.768215e-03
## PctUnemployed 9.156260e-03 9.661646e-03 1.016848e-02 1.067699e-02
## PctEmploy -6.709215e-03 -7.057492e-03 -7.402755e-03 -7.745386e-03
## PctEmplManu -1.422045e-03 -1.553852e-03 -1.696391e-03 -1.850043e-03
## PctEmplProfServ -1.589503e-03 -1.686950e-03 -1.786929e-03 -1.889549e-03
## PctOccupManu 4.797013e-03 5.008586e-03 5.211212e-03 5.405077e-03
## PctOccupMgmtProf -5.959643e-03 -6.229568e-03 -6.489963e-03 -6.740795e-03
## MalePctDivorce 1.198338e-02 1.277443e-02 1.359294e-02 1.444062e-02
## MalePctNevMarr 6.678813e-03 7.068191e-03 7.462667e-03 7.861925e-03
## FemalePctDiv 1.308138e-02 1.393064e-02 1.480690e-02 1.571131e-02
## TotalPctDiv 1.245418e-02 1.326786e-02 1.410863e-02 1.497759e-02
## PersPerFam 3.524816e-03 3.737259e-03 3.955593e-03 4.179555e-03
## PctFam2Par -1.435776e-02 -1.529061e-02 -1.625475e-02 -1.725163e-02
## PctKids2Par -1.481031e-02 -1.578352e-02 -1.679192e-02 -1.783680e-02
## PctYoungKids2Par -1.239639e-02 -1.319490e-02 -1.402013e-02 -1.487273e-02
## PctTeen2Par -1.438748e-02 -1.533677e-02 -1.632132e-02 -1.734155e-02
## PctWorkMomYoungKids -5.026161e-04 -5.254179e-04 -5.470531e-04 -5.668261e-04
## PctWorkMom -3.494581e-03 -3.714500e-03 -3.940875e-03 -4.173351e-03
## NumIlleg 1.834034e-02 1.954941e-02 2.079997e-02 2.209053e-02
## PctIlleg 1.384975e-02 1.480580e-02 1.580517e-02 1.684886e-02
## NumImmig 1.320306e-02 1.396016e-02 1.472250e-02 1.548492e-02
## PctImmigRecent 2.607029e-03 2.721576e-03 2.831168e-03 2.934830e-03
## PctImmigRec5 3.503627e-03 3.667438e-03 3.826452e-03 3.979400e-03
## PctImmigRec8 4.445601e-03 4.677183e-03 4.907369e-03 5.134896e-03
## PctImmigRec10 5.562462e-03 5.869234e-03 6.177804e-03 6.486916e-03
## PctRecentImmig 3.717460e-03 3.920144e-03 4.122692e-03 4.323466e-03
## PctRecImmig5 4.046184e-03 4.273586e-03 4.502164e-03 4.730437e-03
## PctRecImmig8 4.212860e-03 4.458295e-03 4.706628e-03 4.956564e-03
## PctRecImmig10 4.461878e-03 4.725315e-03 4.992547e-03 5.262370e-03
## PctSpeakEnglOnly -3.822610e-03 -4.014158e-03 -4.202219e-03 -4.385284e-03
## PctNotSpeakEnglWell 4.856296e-03 5.098379e-03 5.336314e-03 5.568276e-03
## PctLargHouseFam 7.610574e-03 8.067821e-03 8.535577e-03 9.012949e-03
## PctLargHouseOccup 5.933039e-03 6.281526e-03 6.637161e-03 6.998980e-03
## PersPerOccupHous -8.301261e-04 -8.692632e-04 -9.059472e-04 -9.399036e-04
## PersPerOwnOccHous -3.272194e-03 -3.487207e-03 -3.709526e-03 -3.939223e-03
## PersPerRentOccHous 5.025910e-03 5.323730e-03 5.628638e-03 5.940081e-03
## PctPersOwnOccup -9.943361e-03 -1.049789e-02 -1.105716e-02 -1.161904e-02
## PctPersDenseHous 8.307624e-03 8.795496e-03 9.293010e-03 9.798544e-03
## PctHousLess3BR 1.022179e-02 1.078584e-02 1.135368e-02 1.192248e-02
## MedNumBR -5.038219e-03 -5.299122e-03 -5.558473e-03 -5.814397e-03
## HousVacant 1.206331e-02 1.287598e-02 1.372023e-02 1.459490e-02
## PctHousOccup -6.943953e-03 -7.413543e-03 -7.903458e-03 -8.413986e-03
## PctHousOwnOcc -9.316344e-03 -9.818063e-03 -1.032140e-02 -1.082314e-02
## PctVacantBoarded 9.407581e-03 1.004319e-02 1.070590e-02 1.139558e-02
## PctVacMore6Mos 1.078966e-04 9.119296e-05 7.036860e-05 4.549604e-05
## MedYrHousBuilt -1.570110e-03 -1.635065e-03 -1.695856e-03 -1.751151e-03
## PctHousNoPhone 7.532975e-03 7.966486e-03 8.408260e-03 8.857017e-03
## PctWOFullPlumb 6.452903e-03 6.801958e-03 7.153079e-03 7.504120e-03
## OwnOccLowQuart -2.729487e-03 -2.826799e-03 -2.917322e-03 -3.000336e-03
## OwnOccMedVal -2.248189e-03 -2.312514e-03 -2.368773e-03 -2.415964e-03
## OwnOccHiQuart -1.832894e-03 -1.866604e-03 -1.890742e-03 -1.904055e-03
## RentLowQ -3.572976e-03 -3.722250e-03 -3.866983e-03 -4.005695e-03
## RentMedian -3.298408e-03 -3.406037e-03 -3.504055e-03 -3.590318e-03
## RentHighQ -2.626994e-03 -2.706175e-03 -2.776676e-03 -2.836578e-03
## MedRent -3.084006e-03 -3.166389e-03 -3.236370e-03 -3.291351e-03
## MedRentPctHousInc 7.703416e-03 8.181592e-03 8.673727e-03 9.178124e-03
## MedOwnCostPctInc 2.143527e-03 2.330239e-03 2.528605e-03 2.738783e-03
## MedOwnCostPctIncNoMtg 1.023917e-03 1.073846e-03 1.121976e-03 1.167255e-03
## NumInShelters 1.542653e-02 1.643046e-02 1.746797e-02 1.853575e-02
## NumStreet 1.469876e-02 1.569636e-02 1.673509e-02 1.781321e-02
## PctForeignBorn 3.458689e-03 3.669775e-03 3.884776e-03 4.102531e-03
## PctBornSameState -2.128656e-03 -2.304864e-03 -2.491747e-03 -2.689542e-03
## PctSameHouse85 -2.803135e-03 -2.922570e-03 -3.036986e-03 -3.144725e-03
## PctSameCity85 1.985447e-03 2.152179e-03 2.331143e-03 2.522753e-03
## PctSameState85 -4.639265e-04 -4.946536e-04 -5.258927e-04 -5.575696e-04
## LandArea 7.765632e-03 8.284924e-03 8.823294e-03 9.379189e-03
## PopDens 5.586194e-03 5.924898e-03 6.270598e-03 6.621399e-03
## PctUsePubTrans 3.318097e-03 3.566079e-03 3.825879e-03 4.097096e-03
##
## (Intercept) 2.656385e-01 2.668276e-01 2.680098e-01 2.691825e-01
## (Intercept) . . . .
## state -9.042150e-05 -9.736727e-05 -1.047308e-04 -1.125244e-04
## fold -6.951724e-05 -7.470781e-05 -8.026800e-05 -8.623082e-05
## population 1.517555e-02 1.600238e-02 1.683557e-02 1.767031e-02
## householdsize -1.668978e-03 -1.792758e-03 -1.920310e-03 -2.050605e-03
## racepctblack 1.513266e-02 1.618389e-02 1.728912e-02 1.844955e-02
## racePctWhite -1.596205e-02 -1.698709e-02 -1.805382e-02 -1.916209e-02
## racePctAsian 1.398077e-03 1.485573e-03 1.572542e-03 1.657875e-03
## racePctHisp 5.337087e-03 5.540096e-03 5.733064e-03 5.914036e-03
## agePct12t21 -6.383028e-04 -8.573585e-04 -1.103073e-03 -1.376129e-03
## agePct12t29 2.305490e-03 2.190749e-03 2.040070e-03 1.850760e-03
## agePct16t24 5.114886e-04 3.493405e-04 1.584699e-04 -6.271842e-05
## agePct65up 1.929686e-03 2.038860e-03 2.150081e-03 2.262897e-03
## numbUrban 1.520263e-02 1.605879e-02 1.692593e-02 1.779959e-02
## pctUrban 2.076274e-03 2.277205e-03 2.494125e-03 2.727720e-03
## medIncome -7.842369e-03 -8.098801e-03 -8.336611e-03 -8.553095e-03
## pctWWage -7.649673e-03 -8.014100e-03 -8.377581e-03 -8.738344e-03
## pctWFarmSelf -4.987101e-03 -5.340054e-03 -5.708242e-03 -6.090929e-03
## pctWInvInc -1.537289e-02 -1.615958e-02 -1.695518e-02 -1.775753e-02
## pctWSocSec 2.873229e-03 2.995359e-03 3.115249e-03 3.232154e-03
## pctWPubAsst 1.230615e-02 1.292542e-02 1.354807e-02 1.417155e-02
## pctWRetire -2.910388e-03 -3.068658e-03 -3.230762e-03 -3.396754e-03
## medFamInc -8.796134e-03 -9.107332e-03 -9.401489e-03 -9.675840e-03
## perCapInc -6.452312e-03 -6.603446e-03 -6.730997e-03 -6.832511e-03
## whitePerCap -2.112301e-03 -1.970832e-03 -1.792641e-03 -1.575334e-03
## blackPerCap -6.272737e-03 -6.495675e-03 -6.708481e-03 -6.909836e-03
## indianPerCap -1.731398e-03 -1.759138e-03 -1.780214e-03 -1.794447e-03
## AsianPerCap -1.918239e-03 -1.861979e-03 -1.781882e-03 -1.675949e-03
## OtherPerCap -1.284954e-03 -1.196578e-03 -1.083749e-03 -9.444197e-04
## HispPerCap -3.911996e-03 -3.913042e-03 -3.884552e-03 -3.823872e-03
## NumUnderPov 1.793647e-02 1.889922e-02 1.986949e-02 2.084214e-02
## PctPopUnderPov 1.008385e-02 1.052966e-02 1.096872e-02 1.139841e-02
## PctLess9thGrade 7.940992e-03 8.239741e-03 8.524519e-03 8.792646e-03
## PctNotHSGrad 1.062898e-02 1.110978e-02 1.158570e-02 1.205430e-02
## PctBSorMore -5.994127e-03 -6.211380e-03 -6.418212e-03 -6.612921e-03
## PctUnemployed 1.118436e-02 1.168761e-02 1.218366e-02 1.266934e-02
## PctEmploy -8.083125e-03 -8.413651e-03 -8.734624e-03 -9.043713e-03
## PctEmplManu -2.015323e-03 -2.192721e-03 -2.382701e-03 -2.585690e-03
## PctEmplProfServ -1.994599e-03 -2.101857e-03 -2.211094e-03 -2.322077e-03
## PctOccupManu 5.588159e-03 5.758453e-03 5.914004e-03 6.052957e-03
## PctOccupMgmtProf -6.979637e-03 -7.204076e-03 -7.411766e-03 -7.600479e-03
## MalePctDivorce 1.531616e-02 1.621806e-02 1.714463e-02 1.809398e-02
## MalePctNevMarr 8.264147e-03 8.667441e-03 9.069873e-03 9.469508e-03
## FemalePctDiv 1.664192e-02 1.759655e-02 1.857271e-02 1.956769e-02
## TotalPctDiv 1.587310e-02 1.679327e-02 1.773600e-02 1.869895e-02
## PersPerFam 4.408850e-03 4.643231e-03 4.882525e-03 5.126648e-03
## PctFam2Par -1.827971e-02 -1.933732e-02 -2.042261e-02 -2.153365e-02
## PctKids2Par -1.891694e-02 -2.003097e-02 -2.117741e-02 -2.235467e-02
## PctYoungKids2Par -1.575141e-02 -1.665473e-02 -1.758118e-02 -1.852919e-02
## PctTeen2Par -1.839612e-02 -1.948350e-02 -2.060198e-02 -2.174970e-02
## PctWorkMomYoungKids -5.842245e-04 -5.987041e-04 -6.096964e-04 -6.166191e-04
## PctWorkMom -4.411362e-03 -4.654319e-03 -4.901636e-03 -5.152751e-03
## NumIlleg 2.341768e-02 2.477748e-02 2.616549e-02 2.757680e-02
## PctIlleg 1.793680e-02 1.906884e-02 2.024476e-02 2.146428e-02
## NumImmig 1.624125e-02 1.698472e-02 1.770804e-02 1.840345e-02
## PctImmigRecent 3.031156e-03 3.118729e-03 3.196146e-03 3.262054e-03
## PctImmigRec5 4.124506e-03 4.259956e-03 4.383927e-03 4.494624e-03
## PctImmigRec8 5.357983e-03 5.574790e-03 5.783460e-03 5.982146e-03
## PctImmigRec10 6.794756e-03 7.099458e-03 7.399135e-03 7.691917e-03
## PctRecentImmig 4.520727e-03 4.712644e-03 4.897319e-03 5.072820e-03
## PctRecImmig5 4.956708e-03 5.179183e-03 5.395998e-03 5.605255e-03
## PctRecImmig8 5.206540e-03 5.454894e-03 5.699891e-03 5.939760e-03
## PctRecImmig10 5.533242e-03 5.803523e-03 6.071503e-03 6.335434e-03
## PctSpeakEnglOnly -4.561346e-03 -4.728307e-03 -4.884015e-03 -5.026296e-03
## PctNotSpeakEnglWell 5.791866e-03 6.004597e-03 6.203928e-03 6.387316e-03
## PctLargHouseFam 9.498471e-03 9.990632e-03 1.048791e-02 1.098881e-02
## PctLargHouseOccup 7.365805e-03 7.736451e-03 8.109754e-03 8.484599e-03
## PersPerOccupHous -9.702130e-04 -9.958350e-04 -1.015607e-03 -1.028248e-03
## PersPerOwnOccHous -4.175748e-03 -4.418454e-03 -4.666602e-03 -4.919369e-03
## PersPerRentOccHous 6.257346e-03 6.579743e-03 6.906631e-03 7.237443e-03
## PctPersOwnOccup -1.218042e-02 -1.273808e-02 -1.328872e-02 -1.382904e-02
## PctPersDenseHous 1.031025e-02 1.082624e-02 1.134464e-02 1.186360e-02
## PctHousLess3BR 1.248880e-02 1.304903e-02 1.359948e-02 1.413645e-02
## MedNumBR -6.064757e-03 -6.307328e-03 -6.539836e-03 -6.759997e-03
## HousVacant 1.549826e-02 1.642826e-02 1.738258e-02 1.835866e-02
## PctHousOccup -8.945015e-03 -9.496403e-03 -1.006799e-02 -1.065961e-02
## PctHousOwnOcc -1.131990e-02 -1.180815e-02 -1.228431e-02 -1.274476e-02
## PctVacantBoarded 1.211178e-02 1.285396e-02 1.362146e-02 1.441358e-02
## PctVacMore6Mos 1.623904e-05 -1.774993e-05 -5.683204e-05 -1.013848e-04
## MedYrHousBuilt -1.799603e-03 -1.839767e-03 -1.870118e-03 -1.889056e-03
## PctHousNoPhone 9.311289e-03 9.769593e-03 1.023047e-02 1.069249e-02
## PctWOFullPlumb 7.852946e-03 8.197337e-03 8.535021e-03 8.863711e-03
## OwnOccLowQuart -3.074923e-03 -3.140288e-03 -3.195801e-03 -3.241035e-03
## OwnOccMedVal -2.453141e-03 -2.479480e-03 -2.494315e-03 -2.497176e-03
## OwnOccHiQuart -1.905546e-03 -1.894345e-03 -1.869735e-03 -1.831198e-03
## RentLowQ -4.137351e-03 -4.261044e-03 -4.376036e-03 -4.481802e-03
## RentMedian -3.663296e-03 -3.721572e-03 -3.763888e-03 -3.789188e-03
## RentHighQ -2.884565e-03 -2.919417e-03 -2.940043e-03 -2.945515e-03
## MedRent -3.329473e-03 -3.348974e-03 -3.348230e-03 -3.325795e-03
## MedRentPctHousInc 9.693325e-03 1.021778e-02 1.074987e-02 1.128793e-02
## MedOwnCostPctInc 2.960536e-03 3.193453e-03 3.436932e-03 3.690163e-03
## MedOwnCostPctIncNoMtg 1.208603e-03 1.244789e-03 1.274414e-03 1.295902e-03
## NumInShelters 1.963047e-02 2.074836e-02 2.188521e-02 2.303648e-02
## NumStreet 1.892904e-02 2.008067e-02 2.126593e-02 2.248254e-02
## PctForeignBorn 4.321767e-03 4.541107e-03 4.759093e-03 4.974208e-03
## PctBornSameState -2.898224e-03 -3.117676e-03 -3.347683e-03 -3.587929e-03
## PctSameHouse85 -3.244320e-03 -3.334308e-03 -3.413254e-03 -3.479791e-03
## PctSameCity85 2.727539e-03 2.945992e-03 3.178555e-03 3.425611e-03
## PctSameState85 -5.894645e-04 -6.213398e-04 -6.529451e-04 -6.840222e-04
## LandArea 9.950952e-03 1.053664e-02 1.113404e-02 1.174064e-02
## PopDens 6.975446e-03 7.330718e-03 7.685053e-03 8.036179e-03
## PctUsePubTrans 4.379069e-03 4.670945e-03 4.971669e-03 5.279978e-03
##
## (Intercept) 2.703442e-01 2.714944e-01 0.2726334033 2.737630e-01
## (Intercept) . . . .
## state -1.207594e-04 -1.294464e-04 -0.0001385950 -1.482136e-04
## fold -9.263331e-05 -9.951682e-05 -0.0001069273 -1.149153e-04
## population 1.850140e-02 1.932326e-02 0.0201299555 2.091526e-02
## householdsize -2.182387e-03 -2.314161e-03 -0.0024442013 -2.570566e-03
## racepctblack 1.966623e-02 2.094010e-02 0.0222719080 2.366219e-02
## racePctWhite -2.031160e-02 -2.150195e-02 -0.0227325934 -2.400281e-02
## racePctAsian 1.740358e-03 1.818684e-03 0.0018914745 1.957289e-03
## racePctHisp 6.081097e-03 6.232393e-03 0.0063661558 6.480727e-03
## agePct12t21 -1.676895e-03 -2.005392e-03 -0.0023612824 -2.743859e-03
## agePct12t29 1.620337e-03 1.346574e-03 0.0010275297 6.615871e-04
## agePct16t24 -3.155778e-04 -6.011785e-04 -0.0009202682 -1.273235e-03
## agePct65up 2.376793e-03 2.491199e-03 0.0026054830 2.718958e-03
## numbUrban 1.867490e-02 1.954662e-02 0.0204091534 2.125663e-02
## pctUrban 2.978647e-03 3.247530e-03 0.0035349630 3.841512e-03
## medIncome -8.745617e-03 -8.911633e-03 -0.0090487050 -9.154527e-03
## pctWWage -9.094562e-03 -9.444361e-03 -0.0097858319 -1.011705e-02
## pctWFarmSelf -6.487154e-03 -6.895718e-03 -0.0073151673 -7.743789e-03
## pctWInvInc -1.856449e-02 -1.937389e-02 -0.0201836335 -2.099163e-02
## pctWSocSec 3.345316e-03 3.453965e-03 0.0035573353 3.654681e-03
## pctWPubAsst 1.479324e-02 1.541042e-02 0.0160202890 1.662002e-02
## pctWRetire -3.566782e-03 -3.741108e-03 -0.0039201198 -4.104343e-03
## medFamInc -9.927700e-03 -1.015450e-02 -0.0103538116 -1.052344e-02
## perCapInc -6.905704e-03 -6.948508e-03 -0.0069591201 -6.936058e-03
## whitePerCap -1.316765e-03 -1.015086e-03 -0.0006688107 -2.768840e-04
## blackPerCap -7.098603e-03 -7.273870e-03 -0.0074349977 -7.581676e-03
## indianPerCap -1.801832e-03 -1.802570e-03 -0.0017970971 -1.786121e-03
## AsianPerCap -1.542287e-03 -1.379146e-03 -0.0011849602 -9.583971e-04
## OtherPerCap -7.766099e-04 -5.784407e-04 -0.0003481699 -8.423385e-05
## HispPerCap -3.728516e-03 -3.596220e-03 -0.0034250081 -3.213261e-03
## NumUnderPov 2.181168e-02 2.277227e-02 0.0237178221 2.464207e-02
## PctPopUnderPov 1.181612e-02 1.221930e-02 0.0126054742 1.297233e-02
## PctLess9thGrade 9.041489e-03 9.268512e-03 0.0094713229 9.647741e-03
## PctNotHSGrad 1.251320e-02 1.296010e-02 0.0133928956 1.380969e-02
## PctBSorMore -6.793900e-03 -6.959683e-03 -0.0071089838 -7.240759e-03
## PctUnemployed 1.314146e-02 1.359685e-02 0.0140323711 1.444504e-02
## PctEmploy -9.338654e-03 -9.617291e-03 -0.0098776419 -1.011796e-02
## PctEmplManu -2.802079e-03 -3.032214e-03 -0.0032763922 -3.534856e-03
## PctEmplProfServ -2.434566e-03 -2.548322e-03 -0.0026630988 -2.778651e-03
## PctOccupManu 6.173595e-03 6.274394e-03 0.0063540799 6.411683e-03
## PctOccupMgmtProf -7.768159e-03 -7.912989e-03 -0.0080334540 -8.128416e-03
## MalePctDivorce 1.906402e-02 2.005252e-02 0.0210571230 2.207536e-02
## MalePctNevMarr 9.864459e-03 1.025294e-02 0.0106333009 1.100414e-02
## FemalePctDiv 2.057852e-02 2.160200e-02 0.0226347284 2.367315e-02
## TotalPctDiv 1.967958e-02 2.067516e-02 0.0216828199 2.269955e-02
## PersPerFam 5.375625e-03 5.629596e-03 0.0058888320 6.153731e-03
## PctFam2Par -2.266840e-02 -2.382480e-02 -0.0250008016 -2.619443e-02
## PctKids2Par -2.356114e-02 -2.479519e-02 -0.0260552476 -2.733982e-02
## PctYoungKids2Par -1.949715e-02 -2.048346e-02 -0.0214865758 -2.250506e-02
## PctTeen2Par -2.292472e-02 -2.412499e-02 -0.0253484202 -2.659291e-02
## PctWorkMomYoungKids -6.188862e-04 -6.159211e-04 -0.0006071700 -5.921164e-04
## PctWorkMom -5.407146e-03 -5.664382e-03 -0.0059241226 -6.186166e-03
## NumIlleg 2.900605e-02 3.044754e-02 0.0318952434 3.334291e-02
## PctIlleg 2.272712e-02 2.403301e-02 0.0253817066 2.677304e-02
## NumImmig 1.906281e-02 1.967770e-02 0.0202395055 2.073958e-02
## PctImmigRecent 3.315183e-03 3.354380e-03 0.0033786455 3.387169e-03
## PctImmigRec5 4.590317e-03 4.669380e-03 0.0047303278 4.771856e-03
## PctImmigRec8 6.169053e-03 6.342473e-03 0.0065008259 6.642694e-03
## PctImmigRec10 7.975998e-03 8.249672e-03 0.0085113810 8.759746e-03
## PctRecentImmig 5.237218e-03 5.388622e-03 0.0055252186 5.645311e-03
## PctRecImmig5 5.805049e-03 5.993517e-03 0.0061688642 6.329412e-03
## PctRecImmig8 6.172720e-03 6.397020e-03 0.0066109759 6.813005e-03
## PctRecImmig10 6.593560e-03 6.844158e-03 0.0070855738 7.316259e-03
## PctSpeakEnglOnly -5.152994e-03 -5.262016e-03 -0.0053513738 -5.419231e-03
## PctNotSpeakEnglWell 6.552257e-03 6.696344e-03 0.0068173154 6.913110e-03
## PctLargHouseFam 1.149189e-02 1.199583e-02 0.0124994085 1.300160e-02
## PctLargHouseOccup 8.859959e-03 9.234917e-03 0.0096086912 9.980650e-03
## PersPerOccupHous -1.032367e-03 -1.026477e-03 -0.0010090202 -9.784017e-04
## PersPerOwnOccHous -5.175857e-03 -5.435117e-03 -0.0056961685 -5.958032e-03
## PersPerRentOccHous 7.571701e-03 7.909037e-03 0.0082491994 8.592051e-03
## PctPersOwnOccup -1.435581e-02 -1.486594e-02 -0.0153565474 -1.582503e-02
## PctPersDenseHous 1.238142e-02 1.289654e-02 0.0134075947 1.391348e-02
## PctHousLess3BR 1.465632e-02 1.515560e-02 0.0156310464 1.607973e-02
## MedNumBR -6.965561e-03 -7.154357e-03 -0.0073243448 -7.473650e-03
## HousVacant 1.935370e-02 2.036475e-02 0.0213887439 2.242252e-02
## PctHousOccup -1.127113e-02 -1.190242e-02 -0.0125534179 -1.322412e-02
## PctHousOwnOcc -1.318593e-02 -1.360440e-02 -0.0139969099 -1.436045e-02
## PctVacantBoarded 1.522954e-02 1.606850e-02 0.0169296259 1.781201e-02
## PctVacMore6Mos -1.518037e-04 -2.085032e-04 -0.0002719163 -3.424935e-04
## MedYrHousBuilt -1.894934e-03 -1.886079e-03 -0.0018608140 -1.817488e-03
## PctHousNoPhone 1.115436e-02 1.161486e-02 0.0120729642 1.252778e-02
## PctWOFullPlumb 9.181138e-03 9.485087e-03 0.0097734237 1.004412e-02
## OwnOccLowQuart -3.275809e-03 -3.300224e-03 -0.0033146974 -3.319993e-03
## OwnOccMedVal -2.487825e-03 -2.466292e-03 -0.0024328978 -2.388278e-03
## OwnOccHiQuart -1.778441e-03 -1.711433e-03 -0.0016304218 -1.535948e-03
## RentLowQ -4.578076e-03 -4.664882e-03 -0.0047425664 -4.811807e-03
## RentMedian -3.796664e-03 -3.785784e-03 -0.0037563210 -3.708347e-03
## RentHighQ -2.935103e-03 -2.908298e-03 -0.0028648202 -2.804617e-03
## MedRent -3.280445e-03 -3.211202e-03 -0.0031173491 -2.998423e-03
## MedRentPctHousInc 1.183031e-02 1.237538e-02 0.0129215557 1.346732e-02
## MedOwnCostPctInc 3.952125e-03 4.221579e-03 0.0044970714 4.776947e-03
## MedOwnCostPctIncNoMtg 1.307492e-03 1.307225e-03 0.0012929373 1.262249e-03
## NumInShelters 2.419730e-02 2.536256e-02 0.0265269456 2.768503e-02
## NumStreet 2.372804e-02 2.499999e-02 0.0262959397 2.761355e-02
## PctForeignBorn 5.184913e-03 5.389676e-03 0.0055870142 5.775537e-03
## PctBornSameState -3.838005e-03 -4.097409e-03 -0.0043655551 -4.641789e-03
## PctSameHouse85 -3.532639e-03 -3.570636e-03 -0.0035927553 -3.598112e-03
## PctSameCity85 3.687471e-03 3.964369e-03 0.0042564466 4.563746e-03
## PctSameState85 -7.143121e-04 -7.435618e-04 -0.0007715328 -7.980113e-04
## LandArea 1.235370e-02 1.297020e-02 0.0135869234 1.420043e-02
## PopDens 8.381739e-03 8.719338e-03 0.0090465740 9.361076e-03
## PctUsePubTrans 5.594403e-03 5.913272e-03 0.0062347200 6.556705e-03
##
## (Intercept) 0.2748862107 0.2760074693 2.771327e-01 0.2782694544
## (Intercept) . . . .
## state -0.0001583090 -0.0001688866 -1.799498e-04 -0.0001914997
## fold -0.0001235365 -0.0001328513 -1.429254e-04 -0.0001538298
## population 0.0216727147 0.0223956952 2.307754e-02 0.0237116601
## householdsize -0.0026911200 -0.0028035803 -2.905567e-03 -0.0029946731
## racepctblack 0.0251112538 0.0266191189 2.818556e-02 0.0298101198
## racePctWhite -0.0253117028 -0.0266582163 -2.804113e-02 -0.0294591271
## racePctAsian 0.0020146439 0.0020620173 2.097844e-03 0.0021204973
## racePctHisp 0.0065745855 0.0066463757 6.694959e-03 0.0067194762
## agePct12t21 -0.0031520374 -0.0035843587 -4.038980e-03 -0.0045136585
## agePct12t29 0.0002474874 -0.0002156292 -7.281676e-04 -0.0012900037
## agePct16t24 -0.0016600680 -0.0020803172 -2.533043e-03 -0.0030167594
## agePct65up 0.0028308946 0.0029405354 3.047132e-03 0.0031499976
## numbUrban 0.0220829697 0.0228819883 2.364752e-02 0.0243735513
## pctUrban 0.0041677180 0.0045140932 4.881118e-03 0.0052692295
## medIncome -0.0092269609 -0.0092641023 -9.264385e-03 -0.0092267392
## pctWWage -0.0104360978 -0.0107411440 -1.103051e-02 -0.0113028397
## pctWFarmSelf -0.0081796016 -0.0086203607 -9.063562e-03 -0.0095064631
## pctWInvInc -0.0217958947 -0.0225945669 -2.338607e-02 -0.0241692603
## pctWSocSec 0.0037453087 0.0038286230 3.904201e-03 0.0039718847
## pctWPubAsst 0.0172067704 0.0177777483 1.833033e-02 0.0188622057
## pctWRetire -0.0042944486 -0.0044912684 -4.695800e-03 -0.0049092175
## medFamInc -0.0106614452 -0.0107663048 -1.083702e-02 -0.0108732893
## perCapInc -0.0068782456 -0.0067851124 -6.656726e-03 -0.0064939321
## whitePerCap 0.0001612354 0.0006454719 1.175019e-03 0.0017482272
## blackPerCap -0.0077139983 -0.0078325456 -7.938481e-03 -0.0080336344
## indianPerCap -0.0017706551 -0.0017520626 -1.732093e-03 -0.0017129146
## AsianPerCap -0.0006984097 -0.0004042983 -7.577323e-05 0.0002869888
## OtherPerCap 0.0002147018 0.0005496856 9.214201e-04 0.0013302077
## HispPerCap -0.0029598008 -0.0026639810 -2.325779e-03 -0.0019458731
## NumUnderPov 0.0255386783 0.0264014025 2.722423e-02 0.0280015369
## PctPopUnderPov 0.0133177779 0.0136400219 1.393766e-02 0.0142097444
## PctLess9thGrade 0.0097958658 0.0099141591 1.000153e-02 0.0100573853
## PctNotHSGrad 0.0142089035 0.0145893673 1.495039e-02 0.0152918288
## PctBSorMore -0.0073542625 -0.0074491087 -7.525321e-03 -0.0075833509
## PctUnemployed 0.0148320532 0.0151908717 1.551928e-02 0.0158153859
## PctEmploy -0.0103368217 -0.0105331546 -1.070631e-02 -0.0108560528
## PctEmplManu -0.0038077888 -0.0040953126 -4.397484e-03 -0.0047142990
## PctEmplProfServ -0.0028947275 -0.0030110730 -3.127427e-03 -0.0032435277
## PctOccupManu 0.0064466026 0.0064586576 6.448116e-03 0.0064156829
## PctOccupMgmtProf -0.0081971746 -0.0082395224 -8.255760e-03 -0.0082466611
## MalePctDivorce 0.0231047247 0.0241427010 2.518683e-02 0.0262347581
## MalePctNevMarr 0.0113643022 0.0117130170 1.204991e-02 0.0123750885
## FemalePctDiv 0.0247135824 0.0257522399 2.678530e-02 0.0278089136
## TotalPctDiv 0.0237222798 0.0247478793 2.577322e-02 0.0267951434
## PersPerFam 0.0064248100 0.0067026885 6.988048e-03 0.0072815740
## PctFam2Par -0.0274038427 -0.0286273698 -2.986355e-02 -0.0311111023
## PctKids2Par -0.0286475787 -0.0299773678 -3.132822e-02 -0.0326992988
## PctYoungKids2Par -0.0235376167 -0.0245830761 -2.564042e-02 -0.0267086922
## PctTeen2Par -0.0278563785 -0.0291367582 -3.043197e-02 -0.0317398551
## PctWorkMomYoungKids -0.0005702976 -0.0005413237 -5.048993e-04 -0.0004608511
## PctWorkMom -0.0064504730 -0.0067171905 -6.986675e-03 -0.0072595035
## NumIlleg 0.0347841487 0.0362124915 3.762147e-02 0.0390046158
## PctIlleg 0.0282069218 0.0296833195 3.120224e-02 0.0327636516
## NumImmig 0.0211693533 0.0215204434 2.178481e-02 0.0219548210
## PctImmigRecent 0.0033793626 0.0033548909 3.313687e-03 0.0032559611
## PctImmigRec5 0.0047928693 0.0047925116 4.770173e-03 0.0047254875
## PctImmigRec8 0.0067668491 0.0068722785 6.958187e-03 0.0070239886
## PctImmigRec10 0.0089936050 0.0092120262 9.414314e-03 0.0095999897
## PctRecentImmig 0.0057473545 0.0058299885 5.892071e-03 0.0059327088
## PctRecImmig5 0.0064736289 0.0066001654 6.707889e-03 0.0067959161
## PctRecImmig8 0.0070016665 0.0071756925 7.334028e-03 0.0074758659
## PctRecImmig10 0.0075348137 0.0077400190 7.930878e-03 0.0081066547
## PctSpeakEnglOnly -0.0054639426 -0.0054840948 -5.478535e-03 -0.0054463942
## PctNotSpeakEnglWell 0.0069819093 0.0070221780 7.032681e-03 0.0070124880
## PctLargHouseFam 0.0135015200 0.0139984771 1.449190e-02 0.0149812708
## PctLargHouseOccup 0.0103503108 0.0107173187 1.108140e-02 0.0114423083
## PersPerOccupHous -0.0009330237 -0.0008713302 -7.918482e-04 -0.0006932203
## PersPerOwnOccHous -0.0062197563 -0.0064804443 -6.739268e-03 -0.0069954636
## PersPerRentOccHous 0.0089375529 0.0092857301 9.636612e-03 0.0099901544
## PctPersOwnOccup -0.0162691406 -0.0166869724 -1.707699e-02 -0.0174379380
## PctPersDenseHous 0.0144133412 0.0149066010 1.539291e-02 0.0158721022
## PctHousLess3BR 0.0164990916 0.0168869955 1.724171e-02 0.0175618494
## MedNumBR -0.0076006027 -0.0077037544 -7.781879e-03 -0.0078339565
## HousVacant 0.0234629226 0.0245068177 2.555115e-02 0.0265929519
## PctHousOccup -0.0139145970 -0.0146249523 -1.535533e-02 -0.0161058633
## PctHousOwnOcc -0.0146923016 -0.0149900081 -1.525139e-02 -0.0154744429
## PctVacantBoarded 0.0187147235 0.0196367765 2.057707e-02 0.0215343090
## PctVacMore6Mos -0.0004207048 -0.0005070481 -6.020705e-04 -0.0007064118
## MedYrHousBuilt -0.0017544985 -0.0016703154 -1.563494e-03 -0.0014326844
## PctHousNoPhone 0.0129786028 0.0134248256 1.386590e-02 0.0143012195
## PctWOFullPlumb 0.0102952305 0.0105249187 1.073137e-02 0.0109127250
## OwnOccLowQuart -0.0033172238 -0.0033078333 -3.293533e-03 -0.0032761913
## OwnOccMedVal -0.0023333725 -0.0022693969 -2.197768e-03 -0.0021199882
## OwnOccHiQuart -0.0014288273 -0.0013101128 -1.181013e-03 -0.0010427741
## RentLowQ -0.0048736017 -0.0049292199 -4.980117e-03 -0.0050278125
## RentMedian -0.0036422125 -0.0035584811 -3.457830e-03 -0.0033409175
## RentHighQ -0.0027278299 -0.0026347362 -2.525664e-03 -0.0024008885
## MedRent -0.0028541798 -0.0026845301 -2.489451e-03 -0.0022688869
## MedRentPctHousInc 0.0140112279 0.0145518735 1.508786e-02 0.0156177186
## MedOwnCostPctInc 0.0050593695 0.0053423452 5.623757e-03 0.0059013890
## MedOwnCostPctIncNoMtg 0.0012125562 0.0011410227 1.044571e-03 0.0009198800
## NumInShelters 0.0288313242 0.0299603398 3.106663e-02 0.0321448619
## NumStreet 0.0289506501 0.0303053181 3.167592e-02 0.0330611986
## PctForeignBorn 0.0059539859 0.0061212748 6.276528e-03 0.0064191094
## PctBornSameState -0.0049254086 -0.0052156853 -5.511897e-03 -0.0058133551
## PctSameHouse85 -0.0035859623 -0.0035556870 -3.506766e-03 -0.0034387512
## PctSameCity85 0.0048861989 0.0052236121 5.575658e-03 0.0059418616
## PctSameState85 -0.0008228206 -0.0008458366 -8.670055e-04 -0.0008863617
## LandArea 0.0148071336 0.0154032867 1.598505e-02 0.0165485492
## PopDens 0.0096605402 0.0099427525 1.020562e-02 0.0104471702
## PctUsePubTrans 0.0068770336 0.0071933916 7.503384e-03 0.0078045772
##
## (Intercept) 0.2794264218 0.2806136220 0.2818419165 2.831227e-01
## (Intercept) . . . .
## state -0.0002035353 -0.0002160529 -0.0002290470 -2.425100e-04
## fold -0.0001656408 -0.0001784406 -0.0001923170 -2.073632e-04
## population 0.0242917349 0.0248118567 0.0252667033 2.565163e-02
## householdsize -0.0030685318 -0.0031248858 -0.0031616274 -3.176800e-03
## racepctblack 0.0314921780 0.0332310423 0.0350260221 3.687643e-02
## racePctWhite -0.0309108897 -0.0323951973 -0.0339110161 -3.545750e-02
## racePctAsian 0.0021282481 0.0021192223 0.0020913635 2.042447e-03
## racePctHisp 0.0067194382 0.0066948273 0.0066461939 6.574708e-03
## agePct12t21 -0.0050057226 -0.0055120330 -0.0060289585 -6.552399e-03
## agePct12t29 -0.0019003919 -0.0025578722 -0.0032602147 -4.004453e-03
## agePct16t24 -0.0035293743 -0.0040681392 -0.0046296384 -5.209847e-03
## agePct65up 0.0032485906 0.0033426253 0.0034321985 3.517893e-03
## numbUrban 0.0250544024 0.0256848435 0.0262602029 2.677638e-02
## pctUrban 0.0056787943 0.0061100828 0.0065632373 7.038257e-03
## medIncome -0.0091508049 -0.0090371552 -0.0088874636 -8.704492e-03
## pctWWage -0.0115572210 -0.0117934195 -0.0120119870 -1.221426e-02
## pctWFarmSelf -0.0099461079 -0.0103793701 -0.0108029957 -1.121364e-02
## pctWInvInc -0.0249436725 -0.0257097177 -0.0264688080 -2.722324e-02
## pctWSocSec 0.0040318939 0.0040849321 0.0041322442 4.175574e-03
## pctWPubAsst 0.0193715113 0.0198569962 0.0203180444 2.075453e-02
## pctWRetire -0.0051328771 -0.0053683112 -0.0056172117 -5.881400e-03
## medFamInc -0.0108757188 -0.0108458972 -0.0107863746 -1.070038e-02
## perCapInc -0.0062984843 -0.0060730860 -0.0058212782 -5.547104e-03
## whitePerCap 0.0023625277 0.0030144455 0.0036997618 4.413859e-03
## blackPerCap -0.0081205545 -0.0082024618 -0.0082830670 -8.366226e-03
## indianPerCap -0.0016971220 -0.0016877003 -0.0016879264 -1.701206e-03
## AsianPerCap 0.0006833152 0.0011120611 0.0015717100 2.060557e-03
## OtherPerCap 0.0017759222 0.0022580304 0.0027756904 3.327929e-03
## HispPerCap -0.0015256695 -0.0010672467 -0.0005731725 -4.620515e-05
## NumUnderPov 0.0287282613 0.0293999291 0.0300126141 3.056274e-02
## PctPopUnderPov 0.0144557943 0.0146757038 0.0148694975 1.503694e-02
## PctLess9thGrade 0.0100816711 0.0100747707 0.0100373202 9.969899e-03
## PctNotHSGrad 0.0156140713 0.0159179306 0.0162043916 1.647426e-02
## PctBSorMore -0.0076240366 -0.0076484757 -0.0076578029 -7.652915e-03
## PctUnemployed 0.0160775981 0.0163044360 0.0164942757 1.664502e-02
## PctEmploy -0.0109824416 -0.0110856667 -0.0111657404 -1.122218e-02
## PctEmplManu -0.0050456933 -0.0053915534 -0.0057517220 -6.126001e-03
## PctEmplProfServ -0.0033591161 -0.0034739548 -0.0035878527 -3.700700e-03
## PctOccupManu 0.0063624220 0.0062895960 0.0061984412 6.089943e-03
## PctOccupMgmtProf -0.0082133527 -0.0081571145 -0.0080791183 -7.980206e-03
## MalePctDivorce 0.0272841933 0.0283328888 0.0293784926 3.041838e-02
## MalePctNevMarr 0.0126891253 0.0129930517 0.0132882542 1.357635e-02
## FemalePctDiv 0.0288191380 0.0298118744 0.0307826831 3.172660e-02
## TotalPctDiv 0.0278104530 0.0288157723 0.0298074069 3.078119e-02
## PersPerFam 0.0075838792 0.0078954061 0.0082163454 8.546598e-03
## PctFam2Par -0.0323688264 -0.0336354211 -0.0349092355 -3.618804e-02
## PctKids2Par -0.0340897819 -0.0354986571 -0.0369244895 -3.836524e-02
## PctYoungKids2Par -0.0277868568 -0.0288736121 -0.0299671776 -3.106517e-02
## PctTeen2Par -0.0330580131 -0.0343836478 -0.0357133781 -3.704315e-02
## PctWorkMomYoungKids -0.0004091614 -0.0003500095 -0.0002838185 -2.113050e-04
## PctWorkMom -0.0075364731 -0.0078185987 -0.0081071101 -8.403472e-03
## NumIlleg 0.0403554776 0.0416675287 0.0429341235 4.414849e-02
## PctIlleg 0.0343673521 0.0360128481 0.0376992290 3.942514e-02
## NumImmig 0.0220233877 0.0219840031 0.0218308673 2.155904e-02
## PctImmigRecent 0.0031821834 0.0030930518 0.0029894390 2.872342e-03
## PctImmigRec5 0.0046583032 0.0045686377 0.0044566224 4.322460e-03
## PctImmigRec8 0.0070692757 0.0070937723 0.0070972853 7.079673e-03
## PctImmigRec10 0.0097687492 0.0099204094 0.0100548550 1.017202e-02
## PctRecentImmig 0.0059512940 0.0059475498 0.0059215912 5.873999e-03
## PctRecImmig5 0.0068636520 0.0069108376 0.0069376126 6.944584e-03
## PctRecImmig8 0.0076006955 0.0077083549 0.0077990968 7.873652e-03
## PctRecImmig10 0.0082669194 0.0084116003 0.0085410423 8.656055e-03
## PctSpeakEnglOnly -0.0053870972 -0.0053003706 -0.0051862498 -5.045095e-03
## PctNotSpeakEnglWell 0.0069609584 0.0068777142 0.0067626205 6.615790e-03
## PctLargHouseFam 0.0154660649 0.0159455981 0.0164189546 1.688495e-02
## PctLargHouseOccup 0.0117996955 0.0121530531 0.0125016261 1.284441e-02
## PersPerOccupHous -0.0005742196 -0.0004337414 -0.0002707745 -8.437267e-05
## PersPerOwnOccHous -0.0072482982 -0.0074970219 -0.0077408158 -7.978783e-03
## PersPerRentOccHous 0.0103461447 0.0107041133 0.0110632777 1.142255e-02
## PctPersOwnOccup -0.0177687733 -0.0180685133 -0.0183361643 -1.857073e-02
## PctPersDenseHous 0.0163441260 0.0168089775 0.0172666804 1.771733e-02
## PctHousLess3BR 0.0178463361 0.0180942732 0.0183049385 1.847786e-02
## MedNumBR -0.0078591382 -0.0078567237 -0.0078261628 -7.767115e-03
## HousVacant 0.0276293914 0.0286577744 0.0296756133 3.068073e-02
## PctHousOccup -0.0168765754 -0.0176673457 -0.0184778474 -1.930757e-02
## PctHousOwnOcc -0.0156573129 -0.0157981918 -0.0158953537 -1.594727e-02
## PctVacantBoarded 0.0225069637 0.0234931454 0.0244905953 2.549673e-02
## PctVacMore6Mos -0.0008208743 -0.0009465153 -0.0010847396 -1.237348e-03
## MedYrHousBuilt -0.0012766441 -0.0010942528 -0.0008845596 -6.468674e-04
## PctHousNoPhone 0.0147299368 0.0151508571 0.0155623349 1.596232e-02
## PctWOFullPlumb 0.0110670385 0.0111921842 0.0112858842 1.134581e-02
## OwnOccLowQuart -0.0032576709 -0.0032396433 -0.0032234323 -3.209975e-03
## OwnOccMedVal -0.0020374904 -0.0019514775 -0.0018628122 -1.772037e-03
## OwnOccHiQuart -0.0008965427 -0.0007432302 -0.0005834567 -4.176276e-04
## RentLowQ -0.0050737481 -0.0051191787 -0.0051651555 -5.212672e-03
## RentMedian -0.0032082516 -0.0030601027 -0.0028965377 -2.717622e-03
## RentHighQ -0.0022605438 -0.0021045857 -0.0019328666 -1.745344e-03
## MedRent -0.0020226833 -0.0017505903 -0.0014524001 -1.128220e-03
## MedRentPctHousInc 0.0161399001 0.0166527108 0.0171543858 1.764322e-02
## MedOwnCostPctInc 0.0061729347 0.0064359758 0.0066879205 6.925912e-03
## MedOwnCostPctIncNoMtg 0.0007633990 0.0005713791 0.0003399416 6.518006e-05
## NumInShelters 0.0331898741 0.0341968375 0.0351614561 3.608024e-02
## NumStreet 0.0344603310 0.0358730732 0.0372999173 3.874230e-02
## PctForeignBorn 0.0065486361 0.0066649836 0.0067682677 6.858812e-03
## PctBornSameState -0.0061194208 -0.0064295022 -0.0067430071 -7.059253e-03
## PctSameHouse85 -0.0033512415 -0.0032438918 -0.0031164496 -2.968823e-03
## PctSameCity85 0.0063216020 0.0067141269 0.0071186023 7.534194e-03
## PctSameState85 -0.0009040400 -0.0009202713 -0.0009353491 -9.495594e-04
## LandArea 0.0170899004 0.0176053504 0.0180913745 1.854481e-02
## PopDens 0.0106656154 0.0108593568 0.0110270666 1.116777e-02
## PctUsePubTrans 0.0080945478 0.0083709128 0.0086313455 8.873556e-03
##
## (Intercept) 0.2844678051 2.858891e-01 2.873988e-01 0.2890094069
## (Intercept) . . . .
## state -0.0002564333 -2.708074e-04 -2.856229e-04 -0.0003008692
## fold -0.0002236762 -2.413540e-04 -2.604924e-04 -0.0002811811
## population 0.0259626703 2.619646e-02 2.635017e-02 0.0264214815
## householdsize -0.0031685535 -3.135073e-03 -3.074532e-03 -0.0029851269
## racepctblack 0.0387814790 4.074002e-02 4.275032e-02 0.0448099275
## racePctWhite -0.0370338634 -3.863913e-02 -4.027189e-02 -0.0419301238
## racePctAsian 0.0019701783 1.872379e-03 1.747211e-03 0.0015933171
## racePctHisp 0.0064821307 6.370687e-03 6.242887e-03 0.0061013278
## agePct12t21 -0.0070778920 -7.600805e-03 -8.116568e-03 -0.0086208596
## agePct12t29 -0.0047870414 -5.604132e-03 -6.451867e-03 -0.0073266097
## agePct16t24 -0.0058042778 -6.408189e-03 -7.016803e-03 -0.0076254545
## agePct65up 0.0036008102 3.682491e-03 3.764756e-03 0.0038495470
## numbUrban 0.0272297807 2.761723e-02 2.793591e-02 0.0281834306
## pctUrban 0.0075350187 8.053332e-03 8.593022e-03 0.0091539847
## medIncome -0.0084918057 -8.253239e-03 -7.992289e-03 -0.0077117083
## pctWWage -0.0124021699 -1.257782e-02 -1.274311e-02 -0.0128994698
## pctWFarmSelf -0.0116079142 -1.198235e-02 -1.233342e-02 -0.0126575428
## pctWInvInc -0.0279757869 -2.872903e-02 -2.948476e-02 -0.0302435850
## pctWSocSec 0.0042169872 4.258599e-03 4.302315e-03 0.0043497257
## pctWPubAsst 0.0211664518 2.155345e-02 2.191441e-02 0.0222472907
## pctWRetire -0.0061627923 -6.463384e-03 -6.785252e-03 -0.0071305713
## medFamInc -0.0105912663 -1.046192e-02 -1.031423e-02 -0.0101490407
## perCapInc -0.0052545764 -4.947106e-03 -4.627140e-03 -0.0042961672
## whitePerCap 0.0051521925 5.910735e-03 6.686180e-03 0.0074758034
## blackPerCap -0.0084554964 -8.553758e-03 -8.663075e-03 -0.0087848839
## indianPerCap -0.0017308749 -1.780036e-03 -1.851496e-03 -0.0019478270
## AsianPerCap 0.0025769310 3.119365e-03 3.686626e-03 0.0042775790
## OtherPerCap 0.0039138550 4.532828e-03 5.184475e-03 0.0058685424
## HispPerCap 0.0005110487 1.096369e-03 1.707919e-03 0.0023439805
## NumUnderPov 0.0310468337 3.146131e-02 3.180255e-02 0.0320671182
## PctPopUnderPov 0.0151771255 1.528815e-02 1.536719e-02 0.0154108159
## PctLess9thGrade 0.0098726988 9.745322e-03 9.586830e-03 0.0093960257
## PctNotHSGrad 0.0167278060 1.696463e-02 1.718378e-02 0.0173841861
## PctBSorMore -0.0076342418 -7.601703e-03 -7.554908e-03 -0.0074935366
## PctUnemployed 0.0167538596 1.681724e-02 1.683118e-02 0.0167917239
## PctEmploy -0.0112538314 -1.125888e-02 -1.123526e-02 -0.0111811059
## PctEmplManu -0.0065141472 -6.915855e-03 -7.330726e-03 -0.0077582290
## PctEmplProfServ -0.0038125032 -3.923404e-03 -4.033672e-03 -0.0041436732
## PctOccupManu 0.0059647238 5.823157e-03 5.665703e-03 0.0054933413
## PctOccupMgmtProf -0.0078608347 -7.721286e-03 -7.562102e-03 -0.0073845451
## MalePctDivorce 0.0314495377 3.246855e-02 3.347185e-02 0.0344560532
## MalePctNevMarr 0.0138590941 1.413835e-02 1.441621e-02 0.0146951339
## FemalePctDiv 0.0326380125 3.351072e-02 3.433818e-02 0.0351138771
## TotalPctDiv 0.0317323964 3.265589e-02 3.354638e-02 0.0343987399
## PersPerFam 0.0088858210 9.233546e-03 9.589315e-03 0.0099527132
## PctFam2Par -0.0374689561 -3.874862e-02 -4.002358e-02 -0.0412907654
## PctKids2Par -0.0398182682 -4.128056e-02 -4.274916e-02 -0.0442215211
## PctYoungKids2Par -0.0321646337 -3.326235e-02 -3.435520e-02 -0.0354404531
## PctTeen2Par -0.0383683291 -3.968395e-02 -4.098504e-02 -0.0422668683
## PctWorkMomYoungKids -0.0001335198 -5.187038e-05 3.188853e-05 0.0001156996
## PctWorkMom -0.0087094363 -9.027122e-03 -9.359080e-03 -0.0097082943
## NumIlleg 0.0453038853 4.639380e-02 4.741231e-02 0.0483541097
## PctIlleg 0.0411888863 4.298867e-02 4.482279e-02 0.0466897803
## NumImmig 0.0211646800 2.064525e-02 1.999968e-02 0.0192281376
## PctImmigRecent 0.0027428536 2.602182e-03 2.451693e-03 0.0022929505
## PctImmigRec5 0.0041664238 3.988892e-03 3.790406e-03 0.0035716825
## PctImmigRec8 0.0070408535 6.980841e-03 6.899782e-03 0.0067979422
## PctImmigRec10 0.0102718951 1.035462e-02 1.042051e-02 0.0104700086
## PctRecentImmig 0.0058058839 5.718909e-03 5.615218e-03 0.0054972548
## PctRecImmig5 0.0069328808 6.904147e-03 6.860444e-03 0.0068040533
## PctRecImmig8 0.0079332640 7.979648e-03 8.014867e-03 0.0080411209
## PctRecImmig10 0.0087579281 8.848371e-03 8.929374e-03 0.0090030177
## PctSpeakEnglOnly -0.0048776116 -4.684855e-03 -4.468189e-03 -0.0042291833
## PctNotSpeakEnglWell 0.0064376162 6.228814e-03 5.990416e-03 0.0057237121
## PctLargHouseFam 0.0173421917 1.778917e-02 1.822436e-02 0.0186462321
## PctLargHouseOccup 0.0131801996 1.350770e-02 1.382559e-02 0.0141324677
## PersPerOccupHous 0.0001263412 3.621167e-04 6.234807e-04 0.0009106751
## PersPerOwnOccHous -0.0082100190 -8.433763e-03 -8.649571e-03 -0.0088573972
## PersPerRentOccHous 0.0117805993 1.213598e-02 1.248719e-02 0.0128326963
## PctPersOwnOccup -0.0187713593 -1.893759e-02 -1.906954e-02 -0.0191679858
## PctPersDenseHous 0.0181612277 1.859897e-02 1.903155e-02 0.0194602874
## PctHousLess3BR 0.0186130507 1.871124e-02 1.877412e-02 0.0188042973
## MedNumBR -0.0076795601 -7.563923e-03 -7.421141e-03 -0.0072526430
## HousVacant 0.0316713773 3.264641e-02 3.360530e-02 0.0345481533
## PctHousOccup -0.0201559031 -2.102232e-02 -2.190649e-02 -0.0228083673
## PctHousOwnOcc -0.0159528462 -1.591163e-02 -1.582396e-02 -0.0156909431
## PctVacantBoarded 0.0265087611 2.752392e-02 2.853960e-02 0.0295534017
## PctVacMore6Mos -0.0014064907 -1.594498e-03 -1.803648e-03 -0.0020359708
## MedYrHousBuilt -0.0003808545 -8.670392e-05 2.348052e-04 0.0005822754
## PctHousNoPhone 0.0163485756 1.671896e-02 1.707173e-02 0.0174056856
## PctWOFullPlumb 0.0113698108 1.135610e-02 1.130349e-02 0.0112113643
## OwnOccLowQuart -0.0031999645 -3.194173e-03 -3.193819e-03 -0.0032008027
## OwnOccMedVal -0.0016795710 -1.586044e-03 -1.492629e-03 -0.0014011945
## OwnOccHiQuart -0.0002461763 -6.990262e-05 1.097460e-04 0.0002906080
## RentLowQ -0.0052629772 -5.317965e-03 -5.380450e-03 -0.0054541864
## RentMedian -0.0025237704 -2.316123e-03 -2.096739e-03 -0.0018684924
## RentHighQ -0.0015423835 -1.325029e-03 -1.095085e-03 -0.0008549287
## MedRent -0.0007788084 -4.058217e-04 -1.179573e-05 0.0004001606
## MedRentPctHousInc 0.0181177894 1.857709e-02 1.902065e-02 0.0194484308
## MedOwnCostPctInc 0.0071467472 7.346855e-03 7.522398e-03 0.0076694747
## MedOwnCostPctIncNoMtg -0.0002567166 -6.293534e-04 -1.056064e-03 -0.0015398994
## NumInShelters 0.0369507910 3.777191e-02 3.854358e-02 0.0392667764
## NumStreet 0.0402027561 4.168504e-02 4.319401e-02 0.0447355180
## PctForeignBorn 0.0069371102 7.003806e-03 7.059727e-03 0.0071059898
## PctBornSameState -0.0073773481 -7.696091e-03 -8.013948e-03 -0.0083291446
## PctSameHouse85 -0.0028011425 -2.613777e-03 -2.407272e-03 -0.0021822599
## PctSameCity85 0.0079601727 8.395998e-03 8.841346e-03 0.0092960510
## PctSameState85 -0.0009630852 -9.759220e-04 -9.878536e-04 -0.0009985115
## LandArea 0.0189629886 1.934376e-02 1.968552e-02 0.0199871527
## PopDens 0.0112808988 1.136638e-02 1.142458e-02 0.0114563461
## PctUsePubTrans 0.0090952450 9.294061e-03 9.467600e-03 0.0096134766
##
## (Intercept) 0.2906669927 0.2925249693 0.2945364044 2.967110e-01
## (Intercept) . . . .
## state -0.0003170709 -0.0003331857 -0.0003496599 -3.664867e-04
## fold -0.0003040242 -0.0003279517 -0.0003536785 -3.812063e-04
## population 0.0264978220 0.0263902693 0.0262054263 2.593245e-02
## householdsize -0.0028628782 -0.0027025172 -0.0025160008 -2.295949e-03
## racepctblack 0.0469924846 0.0491226748 0.0513048655 5.352072e-02
## racePctWhite -0.0436895858 -0.0453652152 -0.0470704802 -4.878594e-02
## racePctAsian 0.0014119174 0.0012105366 0.0009689244 6.933258e-04
## racePctHisp 0.0059965497 0.0058161680 0.0056353656 5.449573e-03
## agePct12t21 -0.0090717801 -0.0095569769 -0.0100153054 -1.044952e-02
## agePct12t29 -0.0081854891 -0.0091351832 -0.0100922057 -1.106713e-02
## agePct16t24 -0.0082216114 -0.0088373959 -0.0094326640 -1.001170e-02
## agePct65up 0.0039916409 0.0040764410 0.0041735982 4.281637e-03
## numbUrban 0.0283886721 0.0284706608 0.0284862969 2.842346e-02
## pctUrban 0.0097271500 0.0103362929 0.0109636955 1.161141e-02
## medIncome -0.0074751411 -0.0071086256 -0.0067555246 -6.390490e-03
## pctWWage -0.0130986085 -0.0132034453 -0.0133249985 -1.344281e-02
## pctWFarmSelf -0.0129783243 -0.0132341585 -0.0134544685 -1.363258e-02
## pctWInvInc -0.0310527447 -0.0317580291 -0.0325020179 -3.324820e-02
## pctWSocSec 0.0044101266 0.0044479039 0.0045099464 4.583087e-03
## pctWPubAsst 0.0225679268 0.0227970452 0.0230184568 2.320143e-02
## pctWRetire -0.0074932156 -0.0078876156 -0.0083132208 -8.770901e-03
## medFamInc -0.0099250705 -0.0096825653 -0.0094567021 -9.216308e-03
## perCapInc -0.0038951299 -0.0035172085 -0.0031605894 -2.801051e-03
## whitePerCap 0.0083405578 0.0091605596 0.0099642651 1.076589e-02
## blackPerCap -0.0088668667 -0.0090091471 -0.0091855705 -9.381330e-03
## indianPerCap -0.0020455927 -0.0021974418 -0.0023877111 -2.613014e-03
## AsianPerCap 0.0049187367 0.0055563766 0.0062047945 6.869674e-03
## OtherPerCap 0.0066123170 0.0073622221 0.0081342848 8.935078e-03
## HispPerCap 0.0030492956 0.0037290421 0.0044151437 5.115024e-03
## NumUnderPov 0.0322076813 0.0322941556 0.0323087778 3.223664e-02
## PctPopUnderPov 0.0153488175 0.0153080510 0.0152339701 1.510995e-02
## PctLess9thGrade 0.0091172184 0.0088576061 0.0085712635 8.248766e-03
## PctNotHSGrad 0.0175004245 0.0176657609 0.0178174185 1.794854e-02
## PctBSorMore -0.0073712701 -0.0072948989 -0.0072063962 -7.106118e-03
## PctUnemployed 0.0166309098 0.0164846470 0.0162741186 1.599625e-02
## PctEmploy -0.0110172838 -0.0109150560 -0.0107714160 -1.059102e-02
## PctEmplManu -0.0081893182 -0.0086361962 -0.0090921970 -9.556844e-03
## PctEmplProfServ -0.0042828819 -0.0043922509 -0.0045048266 -4.619354e-03
## PctOccupManu 0.0052560519 0.0050752687 0.0048798886 4.678050e-03
## PctOccupMgmtProf -0.0071327458 -0.0069450755 -0.0067343743 -6.514803e-03
## MalePctDivorce 0.0353909662 0.0363238606 0.0372344507 3.811458e-02
## MalePctNevMarr 0.0149431395 0.0152275435 0.0155207282 1.582576e-02
## FemalePctDiv 0.0357799214 0.0364287344 0.0370072964 3.750729e-02
## TotalPctDiv 0.0351396673 0.0358990145 0.0366040573 3.725172e-02
## PersPerFam 0.0103160281 0.0107022752 0.0110845972 1.147172e-02
## PctFam2Par -0.0424401797 -0.0436889792 -0.0449134376 -4.611928e-02
## PctKids2Par -0.0455885530 -0.0470721703 -0.0485409613 -5.000589e-02
## PctYoungKids2Par -0.0364249897 -0.0375039610 -0.0385553277 -3.959156e-02
## PctTeen2Par -0.0434455771 -0.0446902855 -0.0458892511 -4.705183e-02
## PctWorkMomYoungKids 0.0001791319 0.0002591977 0.0003325582 3.965407e-04
## PctWorkMom -0.0100713219 -0.0104663915 -0.0108850591 -1.133572e-02
## NumIlleg 0.0491267349 0.0499089452 0.0505895297 5.117878e-02
## PctIlleg 0.0485411364 0.0504849481 0.0524469844 5.443841e-02
## NumImmig 0.0183023668 0.0172820068 0.0161283493 1.485850e-02
## PctImmigRecent 0.0021009860 0.0019317322 0.0017574925 1.582035e-03
## PctImmigRec5 0.0033079932 0.0030539930 0.0027788997 2.487161e-03
## PctImmigRec8 0.0066539191 0.0065150651 0.0063530104 6.172008e-03
## PctImmigRec10 0.0104831475 0.0105079983 0.0105136498 1.050629e-02
## PctRecentImmig 0.0053841600 0.0052400318 0.0050871314 4.930552e-03
## PctRecImmig5 0.0067500927 0.0066693363 0.0065824055 6.493235e-03
## PctRecImmig8 0.0080704632 0.0080786687 0.0080861354 8.095256e-03
## PctRecImmig10 0.0090759088 0.0091350528 0.0091958199 9.259789e-03
## PctSpeakEnglOnly -0.0039580130 -0.0036798249 -0.0033836595 -3.074787e-03
## PctNotSpeakEnglWell 0.0054126773 0.0050995758 0.0047597164 4.400371e-03
## PctLargHouseFam 0.0190337790 0.0194397380 0.0198196405 2.018136e-02
## PctLargHouseOccup 0.0144261430 0.0147193264 0.0149898748 1.524347e-02
## PersPerOccupHous 0.0012614834 0.0015943332 0.0019546497 2.337927e-03
## PersPerOwnOccHous -0.0090318965 -0.0092392968 -0.0094341396 -9.625810e-03
## PersPerRentOccHous 0.0131684115 0.0135034249 0.0138216353 1.412663e-02
## PctPersOwnOccup -0.0192015150 -0.0192628634 -0.0192848137 -1.928485e-02
## PctPersDenseHous 0.0198859079 0.0203230902 0.0207555455 2.119227e-02
## PctHousLess3BR 0.0187999425 0.0187997408 0.0187669270 1.872027e-02
## MedNumBR -0.0070646366 -0.0068610944 -0.0066333352 -6.389443e-03
## HousVacant 0.0354607526 0.0363837036 0.0372913501 3.819176e-02
## PctHousOccup -0.0237159600 -0.0246653561 -0.0256273597 -2.660897e-02
## PctHousOwnOcc -0.0155444421 -0.0153498238 -0.0151079650 -1.483164e-02
## PctVacantBoarded 0.0305592740 0.0315769581 0.0325799774 3.357355e-02
## PctVacMore6Mos -0.0023256205 -0.0025976218 -0.0029056345 -3.243296e-03
## MedYrHousBuilt 0.0009388308 0.0013256166 0.0017345867 2.159047e-03
## PctHousNoPhone 0.0177240460 0.0180442035 0.0183300837 1.859499e-02
## PctWOFullPlumb 0.0110999865 0.0109433831 0.0107392259 1.049636e-02
## OwnOccLowQuart -0.0031929991 -0.0032527667 -0.0033100504 -3.385192e-03
## OwnOccMedVal -0.0013162855 -0.0012638974 -0.0012033945 -1.154296e-03
## OwnOccHiQuart 0.0004454164 0.0005975708 0.0007593472 9.125446e-04
## RentLowQ -0.0055895279 -0.0057235182 -0.0058650429 -6.035404e-03
## RentMedian -0.0017017999 -0.0014841212 -0.0012513581 -1.020910e-03
## RentHighQ -0.0006741667 -0.0004292069 -0.0001711327 8.934335e-05
## MedRent 0.0007457799 0.0011830970 0.0016371062 2.099457e-03
## MedRentPctHousInc 0.0199147900 0.0203246505 0.0207146261 2.109172e-02
## MedOwnCostPctInc 0.0077636432 0.0078495915 0.0078971731 7.903813e-03
## MedOwnCostPctIncNoMtg -0.0020637751 -0.0026715520 -0.0033448700 -4.085357e-03
## NumInShelters 0.0399907419 0.0406287092 0.0412267890 4.179013e-02
## NumStreet 0.0463526060 0.0479843270 0.0496716036 5.142300e-02
## PctForeignBorn 0.0071421187 0.0071799390 0.0072138872 7.245521e-03
## PctBornSameState -0.0086254338 -0.0089318060 -0.0092335816 -9.525552e-03
## PctSameHouse85 -0.0019809774 -0.0017241476 -0.0014516970 -1.163126e-03
## PctSameCity85 0.0097684651 0.0102403696 0.0107195413 1.120779e-02
## PctSameState85 -0.0009978908 -0.0010041094 -0.0010100020 -1.012271e-03
## LandArea 0.0202597908 0.0204791495 0.0206593903 2.080099e-02
## PopDens 0.0114921905 0.0114784124 0.0114432010 1.138734e-02
## PctUsePubTrans 0.0097242382 0.0098088614 0.0098630271 9.881801e-03
##
## (Intercept) 0.2990614428 3.015985e-01 0.3043314413 0.3072695046
## (Intercept) . . . .
## state -0.0003836394 -4.010964e-04 -0.0004188279 -0.0004367998
## fold -0.0004105552 -4.417335e-04 -0.0004747228 -0.0005094824
## population 0.0255732481 2.512928e-02 0.0246022578 0.0239938802
## householdsize -0.0020423780 -1.754831e-03 -0.0014336772 -0.0010797448
## racepctblack 0.0557668363 5.803885e-02 0.0603324972 0.0626437736
## racePctWhite -0.0505095471 -5.223723e-02 -0.0539646042 -0.0556869213
## racePctAsian 0.0003837140 4.006756e-05 -0.0003376649 -0.0007499803
## racePctHisp 0.0052624702 5.076462e-03 0.0048931334 0.0047135271
## agePct12t21 -0.0108568619 -1.123469e-02 -0.0115810633 -0.0118944292
## agePct12t29 -0.0120562429 -1.305792e-02 -0.0140716224 -0.0150980000
## agePct16t24 -0.0105695465 -1.110288e-02 -0.0116090327 -0.0120861575
## agePct65up 0.0044021582 4.538221e-03 0.0046924172 0.0048674743
## numbUrban 0.0282846362 2.806991e-02 0.0277798423 0.0274147002
## pctUrban 0.0122793053 1.296687e-02 0.0136736067 0.0143987655
## medIncome -0.0060168839 -5.635371e-03 -0.0052458683 -0.0048480482
## pctWWage -0.0135599903 -1.367761e-02 -0.0137967119 -0.0139185398
## pctWFarmSelf -0.0137652330 -1.384911e-02 -0.0138810240 -0.0138580032
## pctWInvInc -0.0339997415 -3.475442e-02 -0.0355103075 -0.0362658412
## pctWSocSec 0.0046703902 4.773043e-03 0.0048924851 0.0050302438
## pctWPubAsst 0.0233468746 2.345060e-02 0.0235093470 0.0235202613
## pctWRetire -0.0092643335 -9.796090e-03 -0.0103689770 -0.0109856521
## medFamInc -0.0089657322 -8.702628e-03 -0.0084259858 -0.0081349675
## perCapInc -0.0024436079 -2.087265e-03 -0.0017328451 -0.0013817782
## whitePerCap 0.0115588650 1.234104e-02 0.0131080592 0.0138545494
## blackPerCap -0.0096004394 -9.842358e-03 -0.0101082251 -0.0103992909
## indianPerCap -0.0028762334 -3.178347e-03 -0.0035206805 -0.0039042487
## AsianPerCap 0.0075473388 8.236165e-03 0.0089334203 0.0096360854
## OtherPerCap 0.0097618157 1.061370e-02 0.0114887564 0.0123847140
## HispPerCap 0.0058230263 6.536853e-03 0.0072524374 0.0079654386
## NumUnderPov 0.0320812118 3.184133e-02 0.0315178045 0.0311115234
## PctPopUnderPov 0.0149361200 1.470748e-02 0.0144213259 0.0140749718
## PctLess9thGrade 0.0078922725 7.499926e-03 0.0070715029 0.0066066941
## PctNotHSGrad 0.0180623226 1.815823e-02 0.0182379327 0.0183032232
## PctBSorMore -0.0069966055 -6.879038e-03 -0.0067562974 -0.0066316264
## PctUnemployed 0.0156509027 1.523562e-02 0.0147498845 0.0141932738
## PctEmploy -0.0103742517 -1.012014e-02 -0.0098288583 -0.0094998384
## PctEmplManu -0.0100289935 -1.050715e-02 -0.0109896471 -0.0114746177
## PctEmplProfServ -0.0047363503 -4.856511e-03 -0.0049802651 -0.0051080907
## PctOccupManu 0.0044741439 4.272264e-03 0.0040777513 0.0038958289
## PctOccupMgmtProf -0.0062901648 -6.064868e-03 -0.0058438840 -0.0056315843
## MalePctDivorce 0.0389658007 3.978782e-02 0.0405820528 0.0413501143
## MalePctNevMarr 0.0161479987 1.649100e-02 0.0168586785 0.0172542741
## FemalePctDiv 0.0379255161 3.825677e-02 0.0384969084 0.0386414710
## TotalPctDiv 0.0378401002 3.836594e-02 0.0388267637 0.0392197062
## PersPerFam 0.0118618574 1.225399e-02 0.0126467778 0.0130389431
## PctFam2Par -0.0473062770 -4.847294e-02 -0.0496183344 -0.0507406319
## PctKids2Par -0.0514658767 -5.291972e-02 -0.0543661820 -0.0558032869
## PctYoungKids2Par -0.0406101988 -4.160963e-02 -0.0425880117 -0.0435430665
## PctTeen2Par -0.0481720213 -4.924475e-02 -0.0502643614 -0.0512248612
## PctWorkMomYoungKids 0.0004480867 4.841411e-04 0.0005019260 0.0004988708
## PctWorkMom -0.0118223837 -1.234945e-02 -0.0129210785 -0.0135413545
## NumIlleg 0.0516722571 5.206634e-02 0.0523569364 0.0525398661
## PctIlleg 0.0564560659 5.849831e-02 0.0605629667 0.0626479660
## NumImmig 0.0134744616 1.197978e-02 0.0103767545 0.0086675100
## PctImmigRecent 0.0014077715 1.236618e-03 0.0010705887 0.0009115052
## PctImmigRec5 0.0021796620 1.857057e-03 0.0015198375 0.0011682461
## PctImmigRec8 0.0059719933 5.752837e-03 0.0055141892 0.0052555866
## PctImmigRec10 0.0104857117 1.045210e-02 0.0104054003 0.0103456489
## PctRecentImmig 0.0047724509 4.615106e-03 0.0044599554 0.0043081704
## PctRecImmig5 0.0064035870 6.315426e-03 0.0062300555 0.0061488030
## PctRecImmig8 0.0081077282 8.125488e-03 0.0081501015 0.0081834516
## PctRecImmig10 0.0093285589 9.404026e-03 0.0094879573 0.0095825815
## PctSpeakEnglOnly -0.0027543931 -2.424555e-03 -0.0020872934 -0.0017450540
## PctNotSpeakEnglWell 0.0040218940 3.626063e-03 0.0032145275 0.0027892708
## PctLargHouseFam 0.0205202739 2.083401e-02 0.0211199772 0.0213760626
## PctLargHouseOccup 0.0154756323 1.568425e-02 0.0158669252 0.0160216188
## PersPerOccupHous 0.0027433240 3.170849e-03 0.0036207455 0.0040935807
## PersPerOwnOccHous -0.0098145896 -1.000144e-02 -0.0101872038 -0.0103729911
## PersPerRentOccHous 0.0144146473 1.468390e-02 0.0149319779 0.0151563800
## PctPersOwnOccup -0.0192625869 -1.922118e-02 -0.0191636715 -0.0190940221
## PctPersDenseHous 0.0216331640 2.208071e-02 0.0225369451 0.0230040624
## PctHousLess3BR 0.0186615516 1.859637e-02 0.0185297966 0.0184674182
## MedNumBR -0.0061306023 -5.859758e-03 -0.0055796323 -0.0052931806
## HousVacant 0.0390860590 3.997758e-02 0.0408700950 0.0417686040
## PctHousOccup -0.0276097452 -2.863042e-02 -0.0296715900 -0.0307339728
## PctHousOwnOcc -0.0145211629 -1.418085e-02 -0.0138149537 -0.0134287140
## PctVacantBoarded 0.0345543826 3.552113e-02 0.0364723633 0.0374070935
## PctVacMore6Mos -0.0036121227 -4.013038e-03 -0.0044469040 -0.0049147534
## MedYrHousBuilt 0.0025960191 3.041003e-03 0.0034893824 0.0039361442
## PctHousNoPhone 0.0188363229 1.905474e-02 0.0192505197 0.0194241683
## PctWOFullPlumb 0.0102141375 9.894695e-03 0.0095398990 0.0091518901
## OwnOccLowQuart -0.0034793078 -3.596022e-03 -0.0037385146 -0.0039095455
## OwnOccMedVal -0.0011169874 -1.094768e-03 -0.0010900314 -0.0011046790
## OwnOccHiQuart 0.0010568923 1.188957e-03 0.0013065635 0.0014080313
## RentLowQ -0.0062367562 -6.475299e-03 -0.0067559684 -0.0070835444
## RentMedian -0.0007926581 -5.703748e-04 -0.0003559548 -0.0001508101
## RentHighQ 0.0003526498 6.163921e-04 0.0008799413 0.0011431360
## MedRent 0.0025702052 3.046808e-03 0.0035287643 0.0040161325
## MedRentPctHousInc 0.0214547881 2.180625e-02 0.0221481451 0.0224832377
## MedOwnCostPctInc 0.0078672226 7.785554e-03 0.0076578688 0.0074837006
## MedOwnCostPctIncNoMtg -0.0048947087 -5.773672e-03 -0.0067228865 -0.0077425553
## NumInShelters 0.0423218159 4.282821e-02 0.0433161021 0.0437937397
## NumStreet 0.0532464398 5.515190e-02 0.0571493208 0.0592489638
## PctForeignBorn 0.0072777243 7.313820e-03 0.0073576350 0.0074128666
## PctBornSameState -0.0098065459 -1.007438e-02 -0.0103274997 -0.0105643795
## PctSameHouse85 -0.0008584622 -5.387650e-04 -0.0002051257 0.0001409451
## PctSameCity85 0.0117045299 1.220978e-02 0.0127229284 0.0132431925
## PctSameState85 -0.0010111878 -1.006139e-03 -0.0009970886 -0.0009839827
## LandArea 0.0209053836 2.097514e-02 0.0210133986 0.0210240895
## PopDens 0.0113129173 1.122286e-02 0.0111200852 0.0110073957
## PctUsePubTrans 0.0098645096 9.809855e-03 0.0097172108 0.0095861176
##
## (Intercept) 3.104225e-01 0.3138011869 3.174169e-01 3.212798e-01
## (Intercept) . . . .
## state -4.549731e-04 -0.0004733052 -4.917507e-04 -5.102617e-04
## fold -5.459456e-04 -0.0005840200 -6.235874e-04 -6.645049e-04
## population 2.330559e-02 0.0225387113 2.169469e-02 2.077532e-02
## householdsize -6.938832e-04 -0.0002764897 1.726834e-04 6.544534e-04
## racepctblack 6.496869e-02 0.0673031379 6.964296e-02 7.198406e-02
## racePctWhite -5.739911e-02 -0.0590959671 -6.077235e-02 -6.242334e-02
## racePctAsian -1.197508e-03 -0.0016807741 -2.200014e-03 -2.755080e-03
## racePctHisp 4.538583e-03 0.0043695897 4.208375e-03 4.057235e-03
## agePct12t21 -1.217384e-02 -0.0124188594 -1.262944e-02 -1.280580e-02
## agePct12t29 -1.613895e-02 -0.0171973603 -1.827677e-02 -1.938118e-02
## agePct16t24 -1.253317e-02 -0.0129495272 -1.333495e-02 -1.368922e-02
## agePct65up 5.065745e-03 0.0052890810 5.538798e-03 5.815782e-03
## numbUrban 2.697470e-02 0.0264601729 2.587180e-02 2.521067e-02
## pctUrban 1.514140e-02 0.0159003486 1.667422e-02 1.746139e-02
## medIncome -4.441227e-03 -0.0040246030 -3.597466e-03 -3.159260e-03
## pctWWage -1.404438e-02 -0.0141756556 -1.431400e-02 -1.446134e-02
## pctWFarmSelf -1.377730e-02 -0.0136363611 -1.343288e-02 -1.316481e-02
## pctWInvInc -3.702026e-02 -0.0377738634 -3.852809e-02 -3.928529e-02
## pctWSocSec 5.187817e-03 0.0053666194 5.567998e-03 5.793236e-03
## pctWPubAsst 2.348132e-02 0.0233913738 2.325014e-02 2.305797e-02
## pctWRetire -1.164884e-02 -0.0123613854 -1.312623e-02 -1.394638e-02
## medFamInc -7.829345e-03 -0.0075093876 -7.175797e-03 -6.829472e-03
## perCapInc -1.036603e-03 -0.0007007382 -3.782543e-04 -7.348911e-05
## whitePerCap 1.457385e-02 0.0152584174 1.590018e-02 1.649098e-02
## blackPerCap -1.071702e-02 -0.0110626430 -1.143688e-02 -1.183975e-02
## indianPerCap -4.329751e-03 -0.0047973749 -5.306699e-03 -5.856610e-03
## AsianPerCap 1.034079e-02 0.0110440713 1.174247e-02 1.243273e-02
## OtherPerCap 1.329894e-02 0.0142286733 1.517116e-02 1.612371e-02
## HispPerCap 8.671137e-03 0.0093648569 1.004224e-02 1.069947e-02
## NumUnderPov 3.062387e-02 0.0300565958 2.941180e-02 2.869187e-02
## PctPopUnderPov 1.366603e-02 0.0131918691 1.264944e-02 1.203515e-02
## PctLess9thGrade 6.105437e-03 0.0055675671 4.992612e-03 4.379589e-03
## PctNotHSGrad 1.835626e-02 0.0183990035 1.843296e-02 1.845903e-02
## PctBSorMore -6.508496e-03 -0.0063900204 -6.278618e-03 -6.175886e-03
## PctUnemployed 1.356554e-02 0.0128662147 1.209459e-02 1.124987e-02
## PctEmploy -9.131680e-03 -0.0087218508 -8.266877e-03 -7.762716e-03
## PctEmplManu -1.196022e-02 -0.0124447708 -1.292684e-02 -1.340532e-02
## PctEmplProfServ -5.240431e-03 -0.0053776007 -5.519599e-03 -5.665970e-03
## PctOccupManu 3.731419e-03 0.0035888178 3.471734e-03 3.383502e-03
## PctOccupMgmtProf -5.431544e-03 -0.0052463477 -5.077712e-03 -4.926755e-03
## MalePctDivorce 4.209377e-02 0.0428146670 4.351457e-02 4.419567e-02
## MalePctNevMarr 1.768069e-02 0.0181405343 1.863630e-02 1.917050e-02
## FemalePctDiv 3.868575e-02 0.0386247917 3.845373e-02 3.816815e-02
## TotalPctDiv 3.954178e-02 0.0397900327 3.996201e-02 4.005609e-02
## PersPerFam 1.342966e-02 0.0138185849 1.420569e-02 1.459100e-02
## PctFam2Par -5.183753e-02 -0.0529065273 -5.394551e-02 -5.495311e-02
## PctKids2Par -5.722882e-02 -0.0586408027 -6.003793e-02 -6.141979e-02
## PctYoungKids2Par -4.447251e-02 -0.0453744413 -4.624762e-02 -4.709148e-02
## PctTeen2Par -5.212043e-02 -0.0529458574 -5.369668e-02 -5.436907e-02
## PctWorkMomYoungKids 4.725722e-04 0.0004207655 3.413582e-04 2.325029e-04
## PctWorkMom -1.421448e-02 -0.0149448715 -1.573716e-02 -1.659606e-02
## NumIlleg 5.261151e-02 0.0525691328 5.241085e-02 5.213523e-02
## PctIlleg 6.475170e-02 0.0668731968 6.901198e-02 7.116784e-02
## NumImmig 6.854703e-03 0.0049419637 2.933761e-03 8.350717e-04
## PctImmigRecent 7.611541e-04 0.0006213539 4.940029e-04 3.810570e-04
## PctImmigRec5 8.024904e-04 0.0004228513 2.971059e-05 -3.764974e-04
## PctImmigRec8 4.976688e-03 0.0046773748 4.357721e-03 4.017920e-03
## PctImmigRec10 1.027315e-02 0.0101885398 1.009269e-02 9.986566e-03
## PctRecentImmig 4.160961e-03 0.0040197333 3.886003e-03 3.761257e-03
## PctRecImmig5 6.073247e-03 0.0060052579 5.946816e-03 5.899814e-03
## PctRecImmig8 8.227838e-03 0.0082858774 8.360247e-03 8.453463e-03
## PctRecImmig10 9.690536e-03 0.0098146466 9.957622e-03 1.012186e-02
## PctSpeakEnglOnly -1.400582e-03 -0.0010566999 -7.160754e-04 -3.811189e-04
## PctNotSpeakEnglWell 2.352340e-03 0.0019055950 1.450491e-03 9.880287e-04
## PctLargHouseFam 2.160035e-02 0.0217908062 2.194501e-02 2.206004e-02
## PctLargHouseOccup 1.614610e-02 0.0162376990 1.629310e-02 1.630845e-02
## PersPerOccupHous 4.589657e-03 0.0051087368 5.650082e-03 6.212761e-03
## PersPerOwnOccHous -1.056071e-02 -0.0107532133 -1.095406e-02 -1.116714e-02
## PersPerRentOccHous 1.535416e-02 0.0155220960 1.565693e-02 1.575569e-02
## PctPersOwnOccup -1.901691e-02 -0.0189376169 -1.886173e-02 -1.879493e-02
## PctPersDenseHous 2.348403e-02 0.0239786631 2.448975e-02 2.501927e-02
## PctHousLess3BR 1.841498e-02 0.0183782978 1.836296e-02 1.837410e-02
## MedNumBR -5.003351e-03 -0.0047129796 -4.424625e-03 -4.140462e-03
## HousVacant 4.267910e-02 0.0436083495 4.456346e-02 4.555158e-02
## PctHousOccup -3.181835e-02 -0.0329255452 -3.405625e-02 -3.521088e-02
## PctHousOwnOcc -1.302766e-02 -0.0126172776 -1.220256e-02 -1.178780e-02
## PctVacantBoarded 3.832457e-02 0.0392242666 4.010577e-02 4.096870e-02
## PctVacMore6Mos -5.417647e-03 -0.0059565865 -6.532447e-03 -7.145951e-03
## MedYrHousBuilt 4.376074e-03 0.0048038405 5.214114e-03 5.601622e-03
## PctHousNoPhone 1.957615e-02 0.0197069572 1.981704e-02 1.990686e-02
## PctWOFullPlumb 8.732764e-03 0.0082846145 7.809568e-03 7.309886e-03
## OwnOccLowQuart -4.111421e-03 -0.0043460887 -4.615174e-03 -4.920024e-03
## OwnOccMedVal -1.140055e-03 -0.0011971072 -1.276433e-03 -1.378342e-03
## OwnOccHiQuart 1.492265e-03 0.0015585359 1.606423e-03 1.635743e-03
## RentLowQ -7.462496e-03 -0.0078971950 -8.391935e-03 -8.951008e-03
## RentMedian 4.436181e-05 0.0002293630 4.044981e-04 5.705207e-04
## RentHighQ 1.406482e-03 0.0016709569 1.938001e-03 2.209457e-03
## MedRent 4.509779e-03 0.0050111827 5.522405e-03 6.046006e-03
## MedRentPctHousInc 2.281456e-02 0.0231453386 2.347879e-02 2.381813e-02
## MedOwnCostPctInc 7.262908e-03 0.0069955940 6.682109e-03 6.323068e-03
## MedOwnCostPctIncNoMtg -8.832476e-03 -0.0099919667 -1.121982e-02 -1.251426e-02
## NumInShelters 4.427003e-02 0.0447540370 4.525443e-02 4.577931e-02
## NumStreet 6.146056e-02 0.0637928250 6.625301e-02 6.884672e-02
## PctForeignBorn 7.482674e-03 0.0075695864 7.675661e-03 7.802665e-03
## PctBornSameState -1.078358e-02 -0.0109836278 -1.116299e-02 -1.132001e-02
## PctSameHouse85 4.978471e-04 0.0008641184 1.238645e-03 1.620716e-03
## PctSameCity85 1.376970e-02 0.0143017205 1.483881e-02 1.538079e-02
## PctSameState85 -9.666655e-04 -0.0009446818 -9.172627e-04 -8.834154e-04
## LandArea 2.101164e-02 0.0209807716 2.093635e-02 2.088335e-02
## PopDens 1.088709e-02 0.0107608647 1.062981e-02 1.049454e-02
## PctUsePubTrans 9.416206e-03 0.0092070667 8.958225e-03 8.669155e-03
##
## (Intercept) 3.253981e-01 3.297768e-01 0.3344171300 0.3393168717
## (Intercept) . . . .
## state -5.287883e-04 -5.472795e-04 -0.0005656833 -0.0005839472
## fold -7.066070e-04 -7.497081e-04 -0.0007936059 -0.0008380851
## population 1.978287e-02 1.871996e-02 0.0175894869 0.0163945155
## householdsize 1.169978e-03 1.720520e-03 0.0023072756 0.0029312801
## racepctblack 7.432259e-02 7.665504e-02 0.0789782719 0.0812895607
## racePctWhite -6.404430e-02 -6.563081e-02 -0.0671786658 -0.0686838316
## racePctAsian -3.345404e-03 -3.969969e-03 -0.0046272801 -0.0053153459
## racePctHisp 3.918749e-03 3.795609e-03 0.0036905137 0.0036061150
## agePct12t21 -1.294837e-02 -1.305775e-02 -0.0131347399 -0.0131802216
## agePct12t29 -2.051494e-02 -2.168276e-02 -0.0228897486 -0.0241413554
## agePct16t24 -1.401213e-02 -1.430345e-02 -0.0145629564 -0.0147904827
## agePct65up 6.120623e-03 6.453711e-03 0.0068152931 0.0072055145
## numbUrban 2.447816e-02 2.367583e-02 0.0228053131 0.0218682587
## pctUrban 1.826000e-02 1.906802e-02 0.0198832100 0.0207032293
## medIncome -2.709559e-03 -2.247983e-03 -0.0017741369 -0.0012875597
## pctWWage -1.461994e-02 -1.479235e-02 -0.0149814773 -0.0151905331
## pctWFarmSelf -1.283046e-02 -1.242855e-02 -0.0119582766 -0.0114193914
## pctWInvInc -4.004849e-02 -4.082123e-02 -0.0416073908 -0.0424112173
## pctWSocSec 6.043556e-03 6.320126e-03 0.0066240580 0.0069564265
## pctWPubAsst 2.281571e-02 2.252459e-02 0.0221861701 0.0218023176
## pctWRetire -1.482471e-02 -1.576393e-02 -0.0167663591 -0.0178338864
## medFamInc -6.471328e-03 -6.102173e-03 -0.0057226306 -0.0053330960
## perCapInc 2.092251e-04 4.657242e-04 0.0006920942 0.0008847073
## whitePerCap 1.702284e-02 1.748806e-02 0.0178792518 0.0181893430
## blackPerCap -1.227048e-02 -1.272751e-02 -0.0132085362 -0.0137105790
## indianPerCap -6.445293e-03 -7.070248e-03 -0.0077283478 -0.0084159196
## AsianPerCap 1.311183e-02 1.377703e-02 0.0144258785 0.0150562349
## OtherPerCap 1.708379e-02 1.804893e-02 0.0190167910 0.0199851231
## HispPerCap 1.133341e-02 1.194161e-02 0.0125223107 0.0130743864
## NumUnderPov 2.789942e-02 2.703722e-02 0.0261082432 0.0251158143
## PctPopUnderPov 1.134490e-02 1.057418e-02 0.0097182039 0.0087719868
## PctLess9thGrade 3.726942e-03 3.032582e-03 0.0022940019 0.0015084075
## PctNotHSGrad 1.847760e-02 1.848870e-02 0.0184921547 0.0184877865
## PctBSorMore -6.082676e-03 -5.999242e-03 -0.0059253751 -0.0058604876
## PctUnemployed 1.033143e-02 9.339117e-03 0.0082734207 0.0071356171
## PctEmploy -7.205112e-03 -6.589839e-03 -0.0059127918 -0.0051699787
## PctEmplManu -1.387944e-02 -1.434873e-02 -0.0148130066 -0.0152723626
## PctEmplProfServ -5.815756e-03 -5.967509e-03 -0.0061193459 -0.0062689887
## PctOccupManu 3.327309e-03 3.306342e-03 0.0033238176 0.0033829434
## PctOccupMgmtProf -4.794193e-03 -4.680411e-03 -0.0045854133 -0.0045087215
## MalePctDivorce 4.486094e-02 4.551428e-02 0.0461605449 0.0468054543
## MalePctNevMarr 1.974570e-02 2.036452e-02 0.0210296142 0.0217435415
## FemalePctDiv 3.776438e-02 3.723954e-02 0.0365915247 0.0358188273
## TotalPctDiv 4.007168e-02 4.000917e-02 0.0398697753 0.0396554195
## PersPerFam 1.497445e-02 1.535591e-02 0.0157352340 0.0161124227
## PctFam2Par -5.592878e-02 -5.687271e-02 -0.0577855582 -0.0586683247
## PctKids2Par -6.278675e-02 -6.413976e-02 -0.0654801323 -0.0668094551
## PctYoungKids2Par -4.790595e-02 -4.869122e-02 -0.0494476167 -0.0501755098
## PctTeen2Par -5.495960e-02 -5.546508e-02 -0.0558824587 -0.0562089118
## PctWorkMomYoungKids 9.269099e-05 -7.914507e-05 -0.0002835288 -0.0005203421
## PctWorkMom -1.752621e-02 -1.853212e-02 -0.0196180083 -0.0207877658
## NumIlleg 5.174095e-02 5.122660e-02 0.0505907348 0.0498320205
## PctIlleg 7.334063e-02 7.553013e-02 0.0777360894 0.0799582037
## NumImmig -1.348882e-03 -3.612684e-03 -0.0059506555 -0.0083568027
## PctImmigRecent 2.844843e-04 2.062392e-04 0.0001482602 0.0001124707
## PctImmigRec5 -7.953399e-04 -1.226401e-03 -0.0016692714 -0.0021235355
## PctImmigRec8 3.658229e-03 3.278973e-03 0.0028805594 0.0024634907
## PctImmigRec10 9.871166e-03 9.747493e-03 0.0096165499 0.0094793277
## PctRecentImmig 3.646829e-03 3.543828e-03 0.0034530530 0.0033748966
## PctRecImmig5 5.865911e-03 5.846424e-03 0.0058422394 0.0058537377
## PctRecImmig8 8.567749e-03 8.704961e-03 0.0088665444 0.0090535271
## PctRecImmig10 1.030936e-02 1.052167e-02 0.0107599656 0.0110250242
## PctSpeakEnglOnly -5.397936e-05 2.634126e-04 0.0005692841 0.0008619567
## PctNotSpeakEnglWell 5.187705e-04 4.290006e-05 -0.0004397203 -0.0009294984
## PctLargHouseFam 2.213254e-02 2.215884e-02 0.0221350979 0.0220574359
## PctLargHouseOccup 1.627956e-02 1.620209e-02 0.0160717479 0.0158844104
## PersPerOccupHous 6.796018e-03 7.399569e-03 0.0080237889 0.0086698268
## PersPerOwnOccHous -1.139623e-02 -1.164483e-02 -0.0119160370 -0.0122125439
## PersPerRentOccHous 1.581590e-02 1.583568e-02 0.0158137608 0.0157494628
## PctPersOwnOccup -1.874279e-02 -1.871081e-02 -0.0187042870 -0.0187283918
## PctPersDenseHous 2.556948e-02 2.614299e-02 0.0267427061 0.0273718210
## PctHousLess3BR 1.841624e-02 1.849316e-02 0.0186078582 0.0187625599
## MedNumBR -3.862221e-03 -3.591169e-03 -0.0033281237 -0.0030734824
## HousVacant 4.657974e-02 4.765482e-02 0.0487835754 0.0499726111
## PctHousOccup -3.638943e-02 -3.759136e-02 -0.0388155814 -0.0400603626
## PctHousOwnOcc -1.137650e-02 -1.097143e-02 -0.0105746900 -0.0101878147
## PctVacantBoarded 4.181272e-02 4.263753e-02 0.0434428629 0.0442285575
## PctVacMore6Mos -7.797686e-03 -8.488120e-03 -0.0092176153 -0.0099864447
## MedYrHousBuilt 5.961187e-03 6.287736e-03 0.0065763249 0.0068221782
## PctHousNoPhone 1.997691e-02 2.002779e-02 0.0200602518 0.0200752674
## PctWOFullPlumb 6.788032e-03 6.246714e-03 0.0056888845 0.0051177126
## OwnOccLowQuart -5.261738e-03 -5.641226e-03 -0.0060592748 -0.0065166139
## OwnOccMedVal -1.502896e-03 -1.649954e-03 -0.0018192152 -0.0020102422
## OwnOccHiQuart 1.646518e-03 1.638952e-03 0.0016134297 0.0015705205
## RentLowQ -9.578757e-03 -1.027964e-02 -0.0110582387 -0.0119193062
## RentMedian 7.285925e-04 8.802502e-04 0.0010273800 0.0011721904
## RentHighQ 2.487515e-03 2.774674e-03 0.0030736893 0.0033875187
## MedRent 6.584958e-03 7.142587e-03 0.0077225058 0.0083285739
## MedRentPctHousInc 2.416659e-02 2.452740e-02 0.0249038593 0.0252992402
## MedOwnCostPctInc 5.919347e-03 5.472063e-03 0.0049825410 0.0044522863
## MedOwnCostPctIncNoMtg -1.387289e-02 -1.529272e-02 -0.0167701498 -0.0183010268
## NumInShelters 4.633617e-02 4.693200e-02 0.0475732935 0.0482660176
## NumStreet 7.157783e-02 7.444839e-02 0.0774585333 0.0806063369
## PctForeignBorn 7.952202e-03 8.125758e-03 0.0083247066 0.0085503192
## PctBornSameState -1.145291e-02 -1.155977e-02 -0.0116386533 -0.0116876195
## PctSameHouse85 2.009955e-03 2.406200e-03 0.0028093684 0.0032193173
## PctSameCity85 1.592761e-02 1.647930e-02 0.0170357774 0.0175967866
## PctSameState85 -8.420792e-04 -7.922816e-04 -0.0007332639 -0.0006645634
## LandArea 2.082680e-02 2.077187e-02 0.0207236907 0.0206872692
## PopDens 1.035524e-02 1.021178e-02 0.0100637742 0.0099105870
## PctUsePubTrans 8.339323e-03 7.968234e-03 0.0075554717 0.0071007158
##
## (Intercept) 0.3444702352 0.3498682167 0.3554988573 0.3613475139
## (Intercept) . . . .
## state -0.0006020179 -0.0006198415 -0.0006373636 -0.0006545293
## fold -0.0008829220 -0.0009278882 -0.0009727557 -0.0010173001
## population 0.0151382741 0.0138241626 0.0124558099 0.0110371250
## householdsize 0.0035933836 0.0042942801 0.0050345544 0.0058147208
## racepctblack 0.0835865269 0.0858671334 0.0881296491 0.0903726174
## racePctWhite -0.0701423745 -0.0715504611 -0.0729043429 -0.0742003581
## racePctAsian -0.0060316806 -0.0067733208 -0.0075368576 -0.0083184786
## racePctHisp 0.0035450003 0.0035096940 0.0035026699 0.0035263656
## agePct12t21 -0.0131950863 -0.0131800947 -0.0131357551 -0.0130622266
## agePct12t29 -0.0254433865 -0.0268019900 -0.0282236703 -0.0297153143
## agePct16t24 -0.0149859476 -0.0151494042 -0.0152810829 -0.0153814165
## agePct65up 0.0076244564 0.0080721771 0.0085487589 0.0090543513
## numbUrban 0.0208664107 0.0198016834 0.0186762568 0.0174926490
## pctUrban 0.0215256207 0.0223478704 0.0231674445 0.0239818284
## medIncome -0.0007876885 -0.0002738343 0.0002548220 0.0007992106
## pctWWage -0.0154230788 -0.0156830417 -0.0159747387 -0.0163028881
## pctWFarmSelf -0.0108121972 -0.0101375922 -0.0093970726 -0.0085927203
## pctWInvInc -0.0432372200 -0.0440901613 -0.0449750202 -0.0458969636
## pctWSocSec 0.0073182805 0.0077106561 0.0081345687 0.0085909814
## pctWPubAsst 0.0213752050 0.0209073012 0.0204013598 0.0198603970
## pctWRetire -0.0189678566 -0.0201690072 -0.0214374314 -0.0227725683
## medFamInc -0.0049336904 -0.0045242263 -0.0041041827 -0.0036726929
## perCapInc 0.0010402318 0.0011556226 0.0012280988 0.0012551159
## whitePerCap 0.0184115157 0.0185391688 0.0185658624 0.0184852718
## blackPerCap -0.0142300767 -0.0147629819 -0.0153048785 -0.0158511072
## indianPerCap -0.0091288371 -0.0098626308 -0.0106126000 -0.0113739244
## AsianPerCap 0.0156662417 0.0162543334 0.0168192298 0.0173599314
## OtherPerCap 0.0209517294 0.0219144717 0.0228712560 0.0238200285
## HispPerCap 0.0135973324 0.0140912050 0.0145565834 0.0149945285
## NumUnderPov 0.0240637473 0.0229565060 0.0217993114 0.0205981901
## PctPopUnderPov 0.0077304621 0.0065885625 0.0053412957 0.0039838116
## PctLess9thGrade 0.0006728657 -0.0002155658 -0.0011597322 -0.0021623031
## PctNotHSGrad 0.0184754934 0.0184553216 0.0184274752 0.0183923021
## PctBSorMore -0.0058036390 -0.0057535164 -0.0057083878 -0.0056660494
## PctUnemployed 0.0059277985 0.0046528774 0.0033145631 0.0019173331
## PctEmploy -0.0043574577 -0.0034712583 -0.0025073151 -0.0014614308
## PctEmplManu -0.0157271465 -0.0161779500 -0.0166255996 -0.0170711458
## PctEmplProfServ -0.0064138112 -0.0065508801 -0.0066770110 -0.0067888443
## PctOccupManu 0.0034868397 0.0036384628 0.0038405513 0.0040956010
## PctOccupMgmtProf -0.0044492712 -0.0044053435 -0.0043745427 -0.0043538105
## MalePctDivorce 0.0474554161 0.0481173783 0.0487986768 0.0495069188
## MalePctNevMarr 0.0225087441 0.0233274559 0.0242016680 0.0251331196
## FemalePctDiv 0.0349204413 0.0338957322 0.0327443672 0.0314662737
## TotalPctDiv 0.0393685997 0.0390122979 0.0385899163 0.0381052133
## PersPerFam 0.0164877088 0.0168616685 0.0172352758 0.0176099060
## PctFam2Par -0.0595221944 -0.0603485025 -0.0611487181 -0.0619244444
## PctKids2Par -0.0681295380 -0.0694424276 -0.0707504245 -0.0720560898
## PctYoungKids2Par -0.0508753097 -0.0515474646 -0.0521924473 -0.0528107226
## PctTeen2Par -0.0564418767 -0.0565791272 -0.0566188163 -0.0565595095
## PctWorkMomYoungKids -0.0007887359 -0.0010870549 -0.0014127782 -0.0017624814
## PctWorkMom -0.0220448912 -0.0233924368 -0.0248329746 -0.0263685794
## NumIlleg 0.0489493505 0.0479419110 0.0468091500 0.0455506933
## PctIlleg 0.0821960941 0.0844492574 0.0867169920 0.0889983268
## NumImmig -0.0108248380 -0.0133482725 -0.0159205363 -0.0185350806
## PctImmigRecent 0.0001007656 0.0001149773 0.0001568356 0.0002279318
## PctImmigRec5 -0.0025887787 -0.0030645981 -0.0035506073 -0.0040464257
## PctImmigRec8 0.0020283569 0.0015758323 0.0011066847 0.0006217957
## PctImmigRec10 0.0093367835 0.0091898330 0.0090393562 0.0088862114
## PctRecentImmig 0.0033092552 0.0032554612 0.0032122552 0.0031777904
## PctRecImmig5 0.0058807551 0.0059225919 0.0059780558 0.0060455238
## PctRecImmig8 0.0092665610 0.0095059855 0.0097718999 0.0100642256
## PctRecImmig10 0.0113173443 0.0116371911 0.0119846407 0.0123595987
## PctSpeakEnglOnly 0.0011397963 0.0014011868 0.0016445269 0.0018682391
## PctNotSpeakEnglWell -0.0014270817 -0.0019333457 -0.0024493938 -0.0029765544
## PctLargHouseFam 0.0219219978 0.0217250246 0.0214628968 0.0211321747
## PctLargHouseOccup 0.0156362021 0.0153235592 0.0149432695 0.0144925011
## PersPerOccupHous 0.0093396609 0.0100361114 0.0107628161 0.0115241755
## PersPerOwnOccHous -0.0125366768 -0.0128904786 -0.0132757969 -0.0136943723
## PersPerRentOccHous 0.0156426247 0.0154935302 0.0153028347 0.0150714957
## PctPersOwnOccup -0.0187881044 -0.0188882472 -0.0190335124 -0.0192285037
## PctPersDenseHous 0.0280337304 0.0287320123 0.0294704016 0.0302527868
## PctHousLess3BR 0.0189587602 0.0191972981 0.0194784527 0.0198020419
## MedNumBR -0.0028272652 -0.0025891648 -0.0023585976 -0.0021347504
## HousVacant 0.0512283132 0.0525567654 0.0539636418 0.0554541122
## PctHousOccup -0.0413233577 -0.0426015832 -0.0438914403 -0.0451887448
## PctHousOwnOcc -0.0098118623 -0.0094475282 -0.0090952329 -0.0087551848
## PctVacantBoarded 0.0449944843 0.0457405525 0.0464666830 0.0471727904
## PctVacMore6Mos -0.0107947998 -0.0116427887 -0.0125304209 -0.0134575797
## MedYrHousBuilt 0.0070207517 0.0071678251 0.0072596093 0.0072928583
## PctHousNoPhone 0.0200740739 0.0200582144 0.0200295602 0.0199903082
## PctWOFullPlumb 0.0045365375 0.0039488084 0.0033580140 0.0027676074
## OwnOccLowQuart -0.0070139867 -0.0075522027 -0.0081321680 -0.0087548874
## OwnOccMedVal -0.0022224686 -0.0024551890 -0.0027075305 -0.0029784194
## OwnOccHiQuart 0.0015109958 0.0014358484 0.0013463051 0.0012438290
## RentLowQ -0.0128677264 -0.0139085250 -0.0150468625 -0.0162880370
## RentMedian 0.0013171775 0.0014650767 0.0016188066 0.0017814117
## RentHighQ 0.0037192634 0.0040721066 0.0044492577 0.0048539055
## MedRent 0.0089648535 0.0096355899 0.0103452029 0.0110982882
## MedRentPctHousInc 0.0257167695 0.0261595543 0.0266305117 0.0271322925
## MedOwnCostPctInc 0.0038829583 0.0032763488 0.0026343573 0.0019589601
## MedOwnCostPctIncNoMtg -0.0198807253 -0.0215042089 -0.0231661108 -0.0248608048
## NumInShelters 0.0490154758 0.0498262048 0.0507018629 0.0516451617
## NumStreet 0.0838877428 0.0872965087 0.0908242248 0.0944604006
## PctForeignBorn 0.0088037644 0.0090861095 0.0093983152 0.0097412262
## PctBornSameState -0.0117048791 -0.0116888697 -0.0116383383 -0.0115523958
## PctSameHouse85 0.0036357342 0.0040580579 0.0044854530 0.0049168317
## PctSameCity85 0.0181618325 0.0187301451 0.0193006845 0.0198721677
## PctSameState85 -0.0005860513 -0.0004979288 -0.0004006960 -0.0002951055
## LandArea 0.0206673098 0.0206680493 0.0206931208 0.0207454530
## PopDens 0.0097514057 0.0095852528 0.0094110116 0.0092274502
## PctUsePubTrans 0.0066037700 0.0060645821 0.0054832744 0.0048601769
##
## (Intercept) 0.3673971439 3.736286e-01 3.800211e-01 0.3865522348
## (Intercept) . . . .
## state -0.0006712837 -6.875724e-04 -7.033420e-04 -0.0007185417
## fold -0.0010613053 -1.104567e-03 -1.146895e-03 -0.0011881166
## population 0.0095723255 8.065939e-03 6.522779e-03 0.0049479075
## householdsize 0.0066352372 7.496486e-03 8.398724e-03 0.0093420113
## racepctblack 0.0925948276 9.479529e-02 9.697323e-02 0.0991280784
## racePctWhite -0.0754349453 -7.660466e-02 -7.770622e-02 -0.0787364635
## racePctAsian -0.0091140162 -9.919003e-03 -1.072873e-02 -0.0115383236
## racePctHisp 0.0035831912 3.675525e-03 3.805698e-03 0.0039759554
## agePct12t21 -0.0129592589 -1.282617e-02 -1.266185e-02 -0.0124647837
## agePct12t29 -0.0312842157 -3.293809e-02 -3.468504e-02 -0.0365335540
## agePct16t24 -0.0154510394 -1.549076e-02 -1.550151e-02 -0.0154842740
## agePct65up 0.0095892025 1.015367e-02 1.074821e-02 0.0113733613
## numbUrban 0.0162537547 1.496285e-02 1.362358e-02 0.0122398919
## pctUrban 0.0247885631 2.558528e-02 2.636972e-02 0.0271397868
## medIncome 0.0013603337 1.939214e-03 2.536841e-03 0.0031541210
## pctWWage -0.0166725991 -1.708934e-02 -1.755889e-02 -0.0180872840
## pctWFarmSelf -0.0077271736 -6.803583e-03 -5.825556e-03 -0.0047970942
## pctWInvInc -0.0468613176 -4.787353e-02 -4.893915e-02 -0.0500637207
## pctWSocSec 0.0090807567 9.604601e-03 1.016302e-02 0.0107562626
## pctWPubAsst 0.0192876604 1.868659e-02 1.806076e-02 0.0174138333
## pctWRetire -0.0241732103 -2.563752e-02 -2.716305e-02 -0.0287467450
## medFamInc -0.0032285455 -2.770196e-03 -2.295786e-03 -0.0018031661
## perCapInc 0.0012343413 1.163636e-03 1.041045e-03 0.0008647982
## whitePerCap 0.0182911529 1.797732e-02 1.753765e-02 0.0169660592
## blackPerCap -0.0163968980 -1.693751e-02 -1.746835e-02 -0.0179851309
## indianPerCap -0.0121417714 -1.291140e-02 -1.367823e-02 -0.0144379502
## AsianPerCap 0.0178757134 1.836612e-02 1.883094e-02 0.0192702306
## OtherPerCap 0.0247587767 2.568553e-02 2.659839e-02 0.0274955058
## HispPerCap 0.0154065389 1.579450e-02 1.616065e-02 0.0165075034
## NumUnderPov 0.0193599706 1.809224e-02 1.680331e-02 0.0155021387
## PctPopUnderPov 0.0025114613 9.198499e-04 -7.951150e-04 -0.0026371808
## PctLess9thGrade -0.0032257173 -4.352147e-03 -5.543469e-03 -0.0068012431
## PctNotHSGrad 0.0183502696 1.830195e-02 1.824800e-02 0.0181891845
## PctBSorMore -0.0056237826 -5.578327e-03 -5.525871e-03 -0.0054620488
## PctUnemployed 0.0004664097 -1.032261e-03 -2.572029e-03 -0.0041455632
## PctEmploy -0.0003292691 8.936276e-04 2.211808e-03 0.0036298800
## PctEmplManu -0.0175158459 -1.796114e-02 -1.840861e-02 -0.0188599789
## PctEmplProfServ -0.0068829417 -6.955900e-03 -7.004473e-03 -0.0070257055
## PctOccupManu 0.0044058621 4.773349e-03 5.199850e-03 0.0056869411
## PctOccupMgmtProf -0.0043394593 -4.327212e-03 -4.312243e-03 -0.0042892178
## MalePctDivorce 0.0502498968 5.103552e-02 5.187178e-02 0.0527666407
## MalePctNevMarr 0.0261233212 2.717360e-02 2.828517e-02 0.0294591858
## FemalePctDiv 0.0300616109 2.853074e-02 2.687418e-02 0.0250925630
## TotalPctDiv 0.0375622274 3.696519e-02 3.631841e-02 0.0356262051
## PersPerFam 0.0179872856 1.836940e-02 1.875838e-02 0.0191563632
## PctFam2Par -0.0626774152 -6.340948e-02 -6.412260e-02 -0.0648188080
## PctKids2Par -0.0733622359 -7.467190e-02 -7.598834e-02 -0.0773149578
## PctYoungKids2Par -0.0534026999 -5.396868e-02 -5.450880e-02 -0.0550229829
## PctTeen2Par -0.0564002161 -5.614043e-02 -5.578015e-02 -0.0553199488
## PctWorkMomYoungKids -0.0021318218 -2.515554e-03 -2.907573e-03 -0.0033009953
## PctWorkMom -0.0280008312 -2.973084e-02 -3.155928e-02 -0.0334864500
## NumIlleg 0.0441662462 4.265552e-02 4.101816e-02 0.0392537981
## PctIlleg 0.0912919612 9.359622e-02 9.590901e-02 0.0982278053
## NumImmig -0.0211854353 -2.386521e-02 -2.656809e-02 -0.0292877115
## PctImmigRecent 0.0003296965 4.633875e-04 6.300829e-04 0.0008306739
## PctImmigRec5 -0.0045516549 -5.065851e-03 -5.588503e-03 -0.0061190111
## PctImmigRec8 0.0001221860 -3.909654e-04 -9.163098e-04 -0.0014523264
## PctImmigRec10 0.0087312484 8.575316e-03 8.419265e-03 0.0082639473
## PctRecentImmig 0.0031496634 3.124961e-03 3.100316e-03 0.0030719753
## PctRecImmig5 0.0061230093 6.208224e-03 6.298632e-03 0.0063914938
## PctRecImmig8 0.0103827499 1.072715e-02 1.109703e-02 0.0114918940
## PctRecImmig10 0.0127617998 1.319080e-02 1.364597e-02 0.0141265064
## PctSpeakEnglOnly 0.0020707822 2.250659e-03 2.406420e-03 0.0025366612
## PctNotSpeakEnglWell -0.0035163731 -4.070596e-03 -4.641151e-03 -0.0052301269
## PctLargHouseFam 0.0207296356 2.025231e-02 1.969751e-02 0.0190628832
## PctLargHouseOccup 0.0139688239 1.337023e-02 1.269513e-02 0.0119423946
## PersPerOccupHous 0.0123252792 1.317183e-02 1.407006e-02 0.0150266833
## PersPerOwnOccHous -0.0141479135 -1.463815e-02 -1.516687e-02 -0.0157359458
## PersPerRentOccHous 0.0148007100 1.449185e-02 1.414641e-02 0.0137659254
## PctPersOwnOccup -0.0194777749 -1.978586e-02 -2.015727e-02 -0.0205965369
## PctPersDenseHous 0.0310832169 3.196591e-02 3.290527e-02 0.0339058649
## PctHousLess3BR 0.0201675148 2.057403e-02 2.102055e-02 0.0215058679
## MedNumBR -0.0019166212 -1.703057e-03 -1.492787e-03 -0.0012844547
## HousVacant 0.0570327681 5.870357e-02 6.046981e-02 0.0623340778
## PctHousOccup -0.0464887674 -4.778628e-02 -4.907561e-02 -0.0503507174
## PctHousOwnOcc -0.0084274102 -8.111758e-03 -7.807887e-03 -0.0075152360
## PctVacantBoarded 0.0478587702 4.852449e-02 4.916980e-02 0.0497945150
## PctVacMore6Mos -0.0144239848 -1.542915e-02 -1.647234e-02 -0.0175525271
## MedYrHousBuilt 0.0072649742 7.174099e-03 7.019191e-03 0.0068000784
## PctHousNoPhone 0.0199429527 1.989024e-02 1.983509e-02 0.0197805645
## PctWOFullPlumb 0.0021809319 1.601153e-03 1.031203e-03 0.0004737308
## OwnOccLowQuart -0.0094214436 -1.013297e-02 -1.089060e-02 -0.0116955069
## OwnOccMedVal -0.0032665529 -3.570388e-03 -3.888150e-03 -0.0042178506
## OwnOccHiQuart 0.0011301047 1.007014e-03 8.766055e-04 0.0007410733
## RentLowQ -0.0176374888 -1.910080e-02 -2.068366e-02 -0.0223918653
## RentMedian 0.0019560123 2.145767e-03 2.353848e-03 0.0025834284
## RentHighQ 0.0052891823 5.758134e-03 6.263691e-03 0.0068086321
## MedRent 0.0118996203 1.275415e-02 1.366698e-02 0.0146433533
## MedRentPctHousInc 0.0276672041 2.823714e-02 2.884349e-02 0.0294871287
## MedOwnCostPctInc 0.0012521726 5.160078e-04 -2.475656e-04 -0.0010366599
## MedOwnCostPctIncNoMtg -0.0265824683 -2.832514e-02 -3.008277e-02 -0.0318492708
## NumInShelters 0.0526578405 5.374068e-02 5.489351e-02 0.0561153067
## NumStreet 0.0981926128 1.020067e-01 1.058870e-01 0.1098167250
## PctForeignBorn 0.0101155588 1.052189e-02 1.096065e-02 0.0114321007
## PctBornSameState -0.0114305465 -1.127270e-02 -1.107915e-02 -0.0108505773
## PctSameHouse85 0.0053509097 5.786275e-03 6.221457e-03 0.0066549848
## PctSameCity85 0.0204431091 2.101187e-02 2.157668e-02 0.0221357355
## PctSameState85 -0.0001821139 -6.283448e-05 6.150684e-05 0.0001896145
## LandArea 0.0208272021 2.093971e-02 2.108347e-02 0.0212581359
## PopDens 0.0090332536 8.827063e-03 8.607525e-03 0.0083733380
## PctUsePubTrans 0.0041958604 3.491163e-03 2.747206e-03 0.0019654048
##
## (Intercept) 3.931989e-01 0.4001914928 0.4065853445 0.4137263857
## (Intercept) . . . .
## state -7.331233e-04 -0.0007474824 -0.0007606828 -0.0007728637
## fold -1.228080e-03 -0.0012669860 -0.0013041319 -0.0013394548
## population 3.346585e-03 0.0018513000 0.0001875190 -0.0014148632
## householdsize 1.032612e-02 0.0114168468 0.0123968432 0.0135609688
## racepctblack 1.012595e-01 0.1033259308 0.1055354584 0.1075275963
## racePctWhite -7.969244e-02 -0.0805442989 -0.0814398127 -0.0821416120
## racePctAsian -1.234280e-02 -0.0131417935 -0.0139088381 -0.0147200135
## racePctHisp 4.188422e-03 0.0044385343 0.0047791033 0.0051416622
## agePct12t21 -1.223310e-02 -0.0118280198 -0.0116375667 -0.0111243042
## agePct12t29 -3.849241e-02 -0.0406111689 -0.0427073449 -0.0451715500
## agePct16t24 -1.544004e-02 -0.0154378022 -0.0152580730 -0.0152178709
## agePct65up 1.202967e-02 0.0128020956 0.0134334271 0.0143171371
## numbUrban 1.081603e-02 0.0092725129 0.0078918699 0.0063018138
## pctUrban 2.789354e-02 0.0286201450 0.0293410983 0.0300301097
## medIncome 3.791831e-03 0.0044516526 0.0051138723 0.0057678503
## pctWWage -1.868075e-02 -0.0194758664 -0.0201410848 -0.0211167193
## pctWFarmSelf -3.722526e-03 -0.0025961771 -0.0014905194 -0.0002652580
## pctWInvInc -5.125278e-02 -0.0525903540 -0.0539467822 -0.0554479878
## pctWSocSec 1.138433e-02 0.0121784564 0.0128064427 0.0136500872
## pctWPubAsst 1.674952e-02 0.0161399824 0.0154805234 0.0148660141
## pctWRetire -3.038500e-02 -0.0320233973 -0.0337741637 -0.0355614200
## medFamInc -1.289921e-03 -0.0006936427 -0.0001949198 0.0004041688
## perCapInc 6.333114e-04 0.0003476780 0.0000209513 -0.0004401095
## whitePerCap 1.625655e-02 0.0153195038 0.0144005649 0.0131254131
## blackPerCap -1.848396e-02 -0.0189614705 -0.0194174757 -0.0198622562
## indianPerCap -1.518657e-02 -0.0159218453 -0.0166337569 -0.0173375296
## AsianPerCap 1.968426e-02 0.0200855672 0.0204395501 0.0207830675
## OtherPerCap 2.837512e-02 0.0292302497 0.0300749019 0.0308796036
## HispPerCap 1.683779e-02 0.0171551428 0.0174528444 0.0177431228
## NumUnderPov 1.419828e-02 0.0127956131 0.0116045838 0.0103244202
## PctPopUnderPov -4.609709e-03 -0.0068132878 -0.0089511902 -0.0114154301
## PctLess9thGrade -8.126688e-03 -0.0096444051 -0.0109826439 -0.0126462353
## PctNotHSGrad 1.812640e-02 0.0178886153 0.0179767139 0.0177604714
## PctBSorMore -5.381962e-03 -0.0052144979 -0.0051368454 -0.0049072384
## PctUnemployed -5.744885e-03 -0.0075407008 -0.0090371076 -0.0107873540
## PctEmploy 5.152475e-03 0.0070782783 0.0086472401 0.0107626107
## PctEmplManu -1.931702e-02 -0.0197320630 -0.0202190720 -0.0206815504
## PctEmplProfServ -7.017054e-03 -0.0070462490 -0.0069752329 -0.0068971313
## PctOccupManu 6.235986e-03 0.0067318873 0.0074413259 0.0081470317
## PctOccupMgmtProf -4.252343e-03 -0.0041068481 -0.0039934940 -0.0038658977
## MalePctDivorce 5.372806e-02 0.0547086026 0.0559222304 0.0571079368
## MalePctNevMarr 3.069683e-02 0.0318371695 0.0333157175 0.0346800067
## FemalePctDiv 2.318656e-02 0.0210610448 0.0189711284 0.0166553788
## TotalPctDiv 3.489278e-02 0.0339738461 0.0332540263 0.0323144482
## PersPerFam 1.956541e-02 0.0200820289 0.0203269673 0.0209565829
## PctFam2Par -6.550020e-02 -0.0660072193 -0.0666317352 -0.0673060403
## PctKids2Par -7.865531e-02 -0.0800549143 -0.0812280042 -0.0827806401
## PctYoungKids2Par -5.551091e-02 -0.0560502334 -0.0563284339 -0.0568103012
## PctTeen2Par -5.476101e-02 -0.0541637064 -0.0533328811 -0.0524881194
## PctWorkMomYoungKids -3.688256e-03 -0.0039821442 -0.0044213134 -0.0046434969
## PctWorkMom -3.551232e-02 -0.0376960049 -0.0398289329 -0.0422376132
## NumIlleg 3.736200e-02 0.0352450393 0.0331322234 0.0306704727
## PctIlleg 1.005496e-01 0.1029667389 0.1051924035 0.1075396843
## NumImmig -3.201770e-02 -0.0349049813 -0.0375607350 -0.0404411433
## PctImmigRecent 1.065853e-03 0.0013343298 0.0016326849 0.0019885409
## PctImmigRec5 -6.656681e-03 -0.0071468929 -0.0077519165 -0.0082490558
## PctImmigRec8 -1.997325e-03 -0.0025404086 -0.0031059762 -0.0036651660
## PctImmigRec10 8.110209e-03 0.0079371621 0.0077935397 0.0076284653
## PctRecentImmig 3.035857e-03 0.0029288012 0.0029003603 0.0027874986
## PctRecImmig5 6.483909e-03 0.0065607513 0.0066250061 0.0067193016
## PctRecImmig8 1.191120e-02 0.0123873636 0.0128019711 0.0133443052
## PctRecImmig10 1.463141e-02 0.0152305189 0.0157122016 0.0163496154
## PctSpeakEnglOnly 2.640025e-03 0.0026192059 0.0027763586 0.0027055786
## PctNotSpeakEnglWell -5.839756e-03 -0.0064376473 -0.0071154922 -0.0078382224
## PctLargHouseFam 1.834640e-02 0.0175756973 0.0166937804 0.0156517128
## PctLargHouseOccup 1.111136e-02 0.0101236480 0.0092305226 0.0080216061
## PersPerOccupHous 1.604882e-02 0.0171422289 0.0183352358 0.0196700855
## PersPerOwnOccHous -1.634732e-02 -0.0170214319 -0.0177232842 -0.0184189327
## PersPerRentOccHous 1.335191e-02 0.0129098527 0.0124443745 0.0118928942
## PctPersOwnOccup -2.110817e-02 -0.0217455343 -0.0223688550 -0.0230920489
## PctPersDenseHous 3.497246e-02 0.0360994245 0.0373222121 0.0385885108
## PctHousLess3BR 2.202870e-02 0.0226437486 0.0232115027 0.0238384855
## MedNumBR -1.076644e-03 -0.0008761914 -0.0006700246 -0.0004518270
## HousVacant 6.429823e-02 0.0663083383 0.0685124811 0.0707288039
## PctHousOccup -5.160524e-02 -0.0528448416 -0.0540327673 -0.0552013718
## PctHousOwnOcc -7.232999e-03 -0.0071131866 -0.0067383739 -0.0066029548
## PctVacantBoarded 5.039844e-02 0.0510438134 0.0515538131 0.0521477147
## PctVacMore6Mos -1.866836e-02 -0.0198253932 -0.0210289011 -0.0222446697
## MedYrHousBuilt 6.517505e-03 0.0061644224 0.0057327093 0.0053019930
## PctHousNoPhone 1.972976e-02 0.0198163411 0.0196560367 0.0197289992
## PctWOFullPlumb -6.892911e-05 -0.0005679224 -0.0010915917 -0.0015781215
## OwnOccLowQuart -1.254883e-02 -0.0135125208 -0.0143351662 -0.0154056037
## OwnOccMedVal -4.557325e-03 -0.0049719048 -0.0052406282 -0.0056183028
## OwnOccHiQuart 6.027376e-04 0.0004060414 0.0003065315 0.0001816864
## RentLowQ -2.423119e-02 -0.0263560904 -0.0283588201 -0.0307219694
## RentMedian 2.837666e-03 0.0029764824 0.0033488230 0.0036440390
## RentHighQ 7.395540e-03 0.0079975030 0.0086171809 0.0093985860
## MedRent 1.568860e-02 0.0169085278 0.0179653525 0.0193933350
## MedRentPctHousInc 3.016831e-02 0.0309966579 0.0317193208 0.0325431748
## MedOwnCostPctInc -1.849498e-03 -0.0026312957 -0.0035359016 -0.0043962653
## MedOwnCostPctIncNoMtg -3.361858e-02 -0.0353985765 -0.0371111784 -0.0388908394
## NumInShelters 5.740416e-02 0.0588246883 0.0602250908 0.0617773856
## NumStreet 1.137780e-01 0.1178408933 0.1217419140 0.1257814425
## PctForeignBorn 1.193637e-02 0.0125155936 0.0130577752 0.0137032560
## PctBornSameState -1.058803e-02 -0.0103317820 -0.0099899470 -0.0096698127
## PctSameHouse85 7.085436e-03 0.0074862811 0.0078715586 0.0082904246
## PctSameCity85 2.268716e-02 0.0232684844 0.0237832348 0.0243178148
## PctSameState85 3.201653e-04 0.0005248734 0.0006172439 0.0007815993
## LandArea 2.146251e-02 0.0218015583 0.0219271762 0.0223512677
## PopDens 8.123313e-03 0.0079000735 0.0076081081 0.0073421685
## PctUsePubTrans 1.147462e-03 0.0003247672 -0.0005776836 -0.0014627725
##
## (Intercept) 4.205756e-01 4.273401e-01 0.4343705841 4.409667e-01
## (Intercept) . . . .
## state -7.848166e-04 -7.956455e-04 -0.0008059285 -8.153399e-04
## fold -1.373472e-03 -1.405596e-03 -0.0014361856 -1.465085e-03
## population -2.990755e-03 -4.633397e-03 -0.0061250990 -7.658674e-03
## householdsize 1.471150e-02 1.586906e-02 0.0171609535 1.838362e-02
## racepctblack 1.095982e-01 1.116490e-01 0.1136566011 1.157150e-01
## racePctWhite -8.280845e-02 -8.339320e-02 -0.0838725595 -8.432654e-02
## racePctAsian -1.544339e-02 -1.615705e-02 -0.0168541251 -1.749084e-02
## racePctHisp 5.556894e-03 6.027065e-03 0.0065387279 7.140034e-03
## agePct12t21 -1.070054e-02 -1.023896e-02 -0.0095278833 -8.913422e-03
## agePct12t29 -4.762275e-02 -5.028178e-02 -0.0531976007 -5.612650e-02
## agePct16t24 -1.508251e-02 -1.491553e-02 -0.0148360709 -1.463237e-02
## agePct65up 1.507546e-02 1.589700e-02 0.0168596188 1.773469e-02
## numbUrban 4.772360e-03 3.228540e-03 0.0015799948 1.894579e-05
## pctUrban 3.070214e-02 3.135326e-02 0.0319764570 3.257660e-02
## medIncome 6.524361e-03 7.277400e-03 0.0080886785 8.896378e-03
## pctWWage -2.207249e-02 -2.310781e-02 -0.0244119387 -2.571679e-02
## pctWFarmSelf 9.323841e-04 2.157680e-03 0.0034170479 4.657524e-03
## pctWInvInc -5.701769e-02 -5.865632e-02 -0.0604661618 -6.237330e-02
## pctWSocSec 1.448827e-02 1.531110e-02 0.0163204441 1.728680e-02
## pctWPubAsst 1.423262e-02 1.359437e-02 0.0130277258 1.246820e-02
## pctWRetire -3.734753e-02 -3.919021e-02 -0.0410262183 -4.287941e-02
## medFamInc 1.017056e-03 1.657379e-03 0.0024160580 3.149358e-03
## perCapInc -9.106075e-04 -1.448452e-03 -0.0020490568 -2.678382e-03
## whitePerCap 1.175426e-02 1.023493e-02 0.0083927670 6.486433e-03
## blackPerCap -2.028583e-02 -2.067235e-02 -0.0210534058 -2.139391e-02
## indianPerCap -1.801377e-02 -1.866335e-02 -0.0192941081 -1.989058e-02
## AsianPerCap 2.109795e-02 2.139170e-02 0.0216674302 2.192252e-02
## OtherPerCap 3.166789e-02 3.243363e-02 0.0331628362 3.387578e-02
## HispPerCap 1.801620e-02 1.829337e-02 0.0185660642 1.883536e-02
## NumUnderPov 9.134677e-03 8.014313e-03 0.0069101982 5.942052e-03
## PctPopUnderPov -1.390911e-02 -1.654089e-02 -0.0194043077 -2.231052e-02
## PctLess9thGrade -1.424065e-02 -1.590304e-02 -0.0177713570 -1.956776e-02
## PctNotHSGrad 1.768374e-02 1.764210e-02 0.0174199665 1.737350e-02
## PctBSorMore -4.687401e-03 -4.442954e-03 -0.0040569938 -3.671562e-03
## PctUnemployed -1.244754e-02 -1.403060e-02 -0.0157530914 -1.730932e-02
## PctEmploy 1.286458e-02 1.503272e-02 0.0176463890 2.021234e-02
## PctEmplManu -2.115538e-02 -2.166065e-02 -0.0221335516 -2.264678e-02
## PctEmplProfServ -6.798155e-03 -6.649015e-03 -0.0065281800 -6.378473e-03
## PctOccupManu 8.890769e-03 9.752705e-03 0.0105959161 1.152682e-02
## PctOccupMgmtProf -3.618415e-03 -3.365714e-03 -0.0029997892 -2.539021e-03
## MalePctDivorce 5.845963e-02 5.991583e-02 0.0614868552 6.323163e-02
## MalePctNevMarr 3.614418e-02 3.773905e-02 0.0392974638 4.101099e-02
## FemalePctDiv 1.422835e-02 1.171352e-02 0.0089933993 6.207460e-03
## TotalPctDiv 3.139680e-02 3.048523e-02 0.0293971088 2.838707e-02
## PersPerFam 2.137684e-02 2.184095e-02 0.0224444805 2.287927e-02
## PctFam2Par -6.782199e-02 -6.841230e-02 -0.0689081911 -6.936375e-02
## PctKids2Par -8.415746e-02 -8.556443e-02 -0.0871348739 -8.855777e-02
## PctYoungKids2Par -5.717666e-02 -5.747357e-02 -0.0578267430 -5.803834e-02
## PctTeen2Par -5.157266e-02 -5.053026e-02 -0.0494412463 -4.825688e-02
## PctWorkMomYoungKids -4.910554e-03 -5.132377e-03 -0.0052026986 -5.295217e-03
## PctWorkMom -4.466202e-02 -4.717275e-02 -0.0498766950 -5.258069e-02
## NumIlleg 2.823057e-02 2.563124e-02 0.0227313449 1.982420e-02
## PctIlleg 1.098487e-01 1.121133e-01 0.1143962403 1.166034e-01
## NumImmig -4.322566e-02 -4.594352e-02 -0.0488325861 -5.156842e-02
## PctImmigRecent 2.373749e-03 2.788576e-03 0.0032340090 3.721997e-03
## PctImmigRec5 -8.802075e-03 -9.355970e-03 -0.0098654460 -1.041260e-02
## PctImmigRec8 -4.231789e-03 -4.788298e-03 -0.0053455872 -5.895512e-03
## PctImmigRec10 7.473662e-03 7.333205e-03 0.0071745130 7.026139e-03
## PctRecentImmig 2.640637e-03 2.495769e-03 0.0022562189 2.006734e-03
## PctRecImmig5 6.750996e-03 6.780059e-03 0.0067828124 6.740898e-03
## PctRecImmig8 1.385150e-02 1.437378e-02 0.0149639004 1.552118e-02
## PctRecImmig10 1.696163e-02 1.756807e-02 0.0182702138 1.892243e-02
## PctSpeakEnglOnly 2.673312e-03 2.639964e-03 0.0024516455 2.347695e-03
## PctNotSpeakEnglWell -8.531135e-03 -9.301521e-03 -0.0100971580 -1.093168e-02
## PctLargHouseFam 1.462366e-02 1.347250e-02 0.0122117706 1.090580e-02
## PctLargHouseOccup 6.849789e-03 5.617994e-03 0.0041693394 2.758247e-03
## PersPerOccupHous 2.101249e-02 2.251552e-02 0.0241791179 2.593596e-02
## PersPerOwnOccHous -1.923727e-02 -2.009031e-02 -0.0209794410 -2.194643e-02
## PersPerRentOccHous 1.134517e-02 1.075949e-02 0.0101216507 9.480631e-03
## PctPersOwnOccup -2.393154e-02 -2.485005e-02 -0.0258900131 -2.698012e-02
## PctPersDenseHous 3.995831e-02 4.142059e-02 0.0429816348 4.463720e-02
## PctHousLess3BR 2.451240e-02 2.520581e-02 0.0259894418 2.676312e-02
## MedNumBR -2.325217e-04 -9.728788e-06 0.0002177742 4.540019e-04
## HousVacant 7.305679e-02 7.551810e-02 0.0780182572 8.062252e-02
## PctHousOccup -5.631004e-02 -5.737414e-02 -0.0583806636 -5.932550e-02
## PctHousOwnOcc -6.362781e-03 -6.119834e-03 -0.0060473363 -5.832915e-03
## PctVacantBoarded 5.266788e-02 5.316579e-02 0.0536981147 5.415570e-02
## PctVacMore6Mos -2.349679e-02 -2.477352e-02 -0.0260810939 -2.741101e-02
## MedYrHousBuilt 4.771848e-03 4.207366e-03 0.0036131514 2.950055e-03
## PctHousNoPhone 1.971955e-02 1.971027e-02 0.0198442049 1.987311e-02
## PctWOFullPlumb -2.046435e-03 -2.501578e-03 -0.0029156111 -3.324539e-03
## OwnOccLowQuart -1.643418e-02 -1.750535e-02 -0.0187134686 -1.986543e-02
## OwnOccMedVal -5.981595e-03 -6.304232e-03 -0.0066962701 -7.014958e-03
## OwnOccHiQuart 4.290731e-05 -5.428291e-05 -0.0001747254 -2.597409e-04
## RentLowQ -3.318856e-02 -3.577096e-02 -0.0386943434 -4.165169e-02
## RentMedian 3.967203e-03 4.367229e-03 0.0046711903 5.077851e-03
## RentHighQ 1.014512e-02 1.095018e-02 0.0118262287 1.267835e-02
## MedRent 2.080680e-02 2.229030e-02 0.0240529829 2.577691e-02
## MedRentPctHousInc 3.339338e-02 3.425436e-02 0.0352315071 3.618581e-02
## MedOwnCostPctInc -5.275782e-03 -6.200459e-03 -0.0070914200 -8.032563e-03
## MedOwnCostPctIncNoMtg -4.060441e-02 -4.229695e-02 -0.0439901252 -4.560534e-02
## NumInShelters 6.331065e-02 6.491107e-02 0.0666502784 6.836175e-02
## NumStreet 1.296998e-01 1.335498e-01 0.1374136829 1.411145e-01
## PctForeignBorn 1.435744e-02 1.503467e-02 0.0157969011 1.657281e-02
## PctBornSameState -9.311055e-03 -8.926162e-03 -0.0085423638 -8.136588e-03
## PctSameHouse85 8.674903e-03 9.051257e-03 0.0094067177 9.726929e-03
## PctSameCity85 2.483382e-02 2.532326e-02 0.0258175808 2.628755e-02
## PctSameState85 9.314437e-04 1.061544e-03 0.0012505307 1.398853e-03
## LandArea 2.264129e-02 2.294627e-02 0.0233697311 2.367584e-02
## PopDens 7.039754e-03 6.715525e-03 0.0064102056 6.078755e-03
## PctUsePubTrans -2.391051e-03 -3.349385e-03 -0.0043045220 -5.292591e-03
##
## (Intercept) 0.4475332239 0.4541235916 0.4606683079 0.4673432074
## (Intercept) . . . .
## state -0.0008235222 -0.0008308664 -0.0008375050 -0.0008436412
## fold -0.0014919111 -0.0015169360 -0.0015403518 -0.0015624724
## population -0.0092535522 -0.0108466016 -0.0124250306 -0.0138453049
## householdsize 0.0196118540 0.0208721287 0.0221558882 0.0235733206
## racepctblack 0.1177312052 0.1197006283 0.1216408978 0.1235950481
## racePctWhite -0.0846701775 -0.0848853016 -0.0849804875 -0.0849641027
## racePctAsian -0.0181110232 -0.0186845341 -0.0191970376 -0.0196633208
## racePctHisp 0.0077993307 0.0084883339 0.0092028190 0.0099487395
## agePct12t21 -0.0082652560 -0.0075537100 -0.0067768666 -0.0056975992
## agePct12t29 -0.0593022571 -0.0626878555 -0.0662835869 -0.0702615341
## agePct16t24 -0.0143982370 -0.0141606811 -0.0139124935 -0.0137776522
## agePct65up 0.0186554173 0.0195917815 0.0205406855 0.0216178888
## numbUrban -0.0015397846 -0.0031200973 -0.0047204245 -0.0064340098
## pctUrban 0.0331575482 0.0337163810 0.0342511801 0.0347593747
## medIncome 0.0096920244 0.0105385319 0.0114449425 0.0124718020
## pctWWage -0.0271241664 -0.0286393610 -0.0302617100 -0.0322017065
## pctWFarmSelf 0.0059229902 0.0072049374 0.0084898036 0.0097801897
## pctWInvInc -0.0643499737 -0.0663842300 -0.0684865261 -0.0707976343
## pctWSocSec 0.0182393184 0.0192126623 0.0201989680 0.0213695031
## pctWPubAsst 0.0119024761 0.0113033782 0.0106783569 0.0101426518
## pctWRetire -0.0447796077 -0.0466831698 -0.0485724327 -0.0504181749
## medFamInc 0.0038778697 0.0046508676 0.0055081735 0.0065758197
## perCapInc -0.0034111935 -0.0042204482 -0.0050754289 -0.0059616854
## whitePerCap 0.0044025267 0.0021096243 -0.0003872410 -0.0033080664
## blackPerCap -0.0217088234 -0.0220051776 -0.0222773217 -0.0225606137
## indianPerCap -0.0204602056 -0.0210035449 -0.0215178128 -0.0220116563
## AsianPerCap 0.0221577366 0.0223758269 0.0225806821 0.0227695633
## OtherPerCap 0.0345609751 0.0352177939 0.0358490757 0.0364436981
## HispPerCap 0.0191138296 0.0193984050 0.0196922172 0.0199882410
## NumUnderPov 0.0051062206 0.0043931600 0.0037878230 0.0032937175
## PctPopUnderPov -0.0253495654 -0.0285186132 -0.0318247509 -0.0353758629
## PctLess9thGrade -0.0214238264 -0.0233375509 -0.0253124894 -0.0275085912
## PctNotHSGrad 0.0173646413 0.0173675526 0.0173864668 0.0172497545
## PctBSorMore -0.0032193363 -0.0026825355 -0.0020684301 -0.0012742858
## PctUnemployed -0.0187628413 -0.0201548591 -0.0214772625 -0.0228722438
## PctEmploy 0.0228432716 0.0256002095 0.0285027442 0.0319261499
## PctEmplManu -0.0232061383 -0.0237976476 -0.0244140799 -0.0250017821
## PctEmplProfServ -0.0061692373 -0.0059161501 -0.0056395232 -0.0054358565
## PctOccupManu 0.0125867638 0.0137290720 0.0149385407 0.0161377296
## PctOccupMgmtProf -0.0020686785 -0.0015501361 -0.0009532406 -0.0001703810
## MalePctDivorce 0.0650847262 0.0670489287 0.0691276351 0.0713999664
## MalePctNevMarr 0.0428697676 0.0448115637 0.0468279161 0.0488760958
## FemalePctDiv 0.0033252272 0.0003171443 -0.0028211807 -0.0061850486
## TotalPctDiv 0.0274004970 0.0264058780 0.0253893271 0.0241558161
## PersPerFam 0.0233857025 0.0239442010 0.0245228956 0.0251976823
## PctFam2Par -0.0699568249 -0.0706072486 -0.0712559337 -0.0717689033
## PctKids2Par -0.0900769024 -0.0917183292 -0.0934389436 -0.0953323544
## PctYoungKids2Par -0.0582030563 -0.0583674839 -0.0585131543 -0.0586690582
## PctTeen2Par -0.0469772760 -0.0456605788 -0.0443171511 -0.0429472063
## PctWorkMomYoungKids -0.0053150833 -0.0052456947 -0.0050815689 -0.0047139253
## PctWorkMom -0.0553768292 -0.0582831707 -0.0612918104 -0.0645185313
## NumIlleg 0.0167743644 0.0136318293 0.0104040686 0.0068530290
## PctIlleg 0.1187494708 0.1208543347 0.1229223132 0.1249553644
## NumImmig -0.0542147619 -0.0568049991 -0.0593290217 -0.0619812489
## PctImmigRecent 0.0042349312 0.0047822372 0.0053605738 0.0059647448
## PctImmigRec5 -0.0109643004 -0.0115157543 -0.0120574103 -0.0125378515
## PctImmigRec8 -0.0064311430 -0.0069611888 -0.0074783998 -0.0079825093
## PctImmigRec10 0.0069022647 0.0067922057 0.0066907835 0.0065704810
## PctRecentImmig 0.0017529743 0.0014453482 0.0010717104 0.0005722911
## PctRecImmig5 0.0067040584 0.0066499318 0.0065565748 0.0063855152
## PctRecImmig8 0.0161085310 0.0167331943 0.0173804713 0.0180794740
## PctRecImmig10 0.0195727713 0.0202458908 0.0209357731 0.0217085579
## PctSpeakEnglOnly 0.0022264889 0.0020462601 0.0018139665 0.0014184115
## PctNotSpeakEnglWell -0.0118573663 -0.0128228583 -0.0138202152 -0.0148755326
## PctLargHouseFam 0.0094623729 0.0079381127 0.0063629969 0.0046841250
## PctLargHouseOccup 0.0012712057 -0.0002971526 -0.0019179005 -0.0037445902
## PersPerOccupHous 0.0278604683 0.0299017112 0.0320678372 0.0344982391
## PersPerOwnOccHous -0.0229421655 -0.0239978968 -0.0251445826 -0.0263807016
## PersPerRentOccHous 0.0087843385 0.0080414129 0.0072648451 0.0064182746
## PctPersOwnOccup -0.0281530405 -0.0294451099 -0.0308874248 -0.0325406451
## PctPersDenseHous 0.0463962140 0.0482712894 0.0502754115 0.0524654498
## PctHousLess3BR 0.0275262857 0.0283092094 0.0291376972 0.0301286630
## MedNumBR 0.0007059003 0.0009757334 0.0012583825 0.0015450014
## HousVacant 0.0833273632 0.0861040934 0.0889601541 0.0918809244
## PctHousOccup -0.0601995215 -0.0609900563 -0.0616997319 -0.0623270540
## PctHousOwnOcc -0.0055737168 -0.0052898944 -0.0049949197 -0.0048774764
## PctVacantBoarded 0.0545858490 0.0549907213 0.0553745999 0.0557956456
## PctVacMore6Mos -0.0287442719 -0.0300754997 -0.0314074583 -0.0327652147
## MedYrHousBuilt 0.0022849291 0.0016103503 0.0009212498 0.0002320453
## PctHousNoPhone 0.0199041122 0.0199648580 0.0200611081 0.0203052675
## PctWOFullPlumb -0.0037232781 -0.0041014021 -0.0044561080 -0.0047746892
## OwnOccLowQuart -0.0210944256 -0.0224338803 -0.0238642269 -0.0254343792
## OwnOccMedVal -0.0072904357 -0.0075737247 -0.0078633709 -0.0082117835
## OwnOccHiQuart -0.0002815032 -0.0002730665 -0.0002488288 -0.0002289290
## RentLowQ -0.0447194289 -0.0479625167 -0.0514039562 -0.0552737851
## RentMedian 0.0056117252 0.0062186107 0.0068563159 0.0073419134
## RentHighQ 0.0136263741 0.0146616995 0.0157459091 0.0168779958
## MedRent 0.0276039466 0.0295836005 0.0317105275 0.0342069988
## MedRentPctHousInc 0.0370982732 0.0379938023 0.0389025224 0.0399386321
## MedOwnCostPctInc -0.0090213597 -0.0100150917 -0.0110056456 -0.0119597067
## MedOwnCostPctIncNoMtg -0.0471932220 -0.0487523819 -0.0502724233 -0.0517768627
## NumInShelters 0.0700893445 0.0718088159 0.0735271991 0.0753873653
## NumStreet 0.1446926161 0.1481472423 0.1514684378 0.1547247499
## PctForeignBorn 0.0173588924 0.0181660445 0.0190010835 0.0199337743
## PctBornSameState -0.0077061188 -0.0072511416 -0.0067815951 -0.0063248792
## PctSameHouse85 0.0100542037 0.0103932416 0.0107339807 0.0110583569
## PctSameCity85 0.0267186519 0.0271183593 0.0274951795 0.0278718478
## PctSameState85 0.0015126980 0.0016122693 0.0017129301 0.0018895786
## LandArea 0.0239940191 0.0243156063 0.0246245968 0.0249956003
## PopDens 0.0057159611 0.0053227394 0.0049062921 0.0045076438
## PctUsePubTrans -0.0063013575 -0.0073254369 -0.0083625166 -0.0093953098
##
## (Intercept) 0.4733915931 4.792953e-01 0.4853726101 4.909571e-01
## (Intercept) . . . .
## state -0.0008490723 -8.533795e-04 -0.0008569344 -8.598109e-04
## fold -0.0015832185 -1.602138e-03 -0.0016195978 -1.635743e-03
## population -0.0152398041 -1.666474e-02 -0.0179611304 -1.926276e-02
## householdsize 0.0248773898 2.612621e-02 0.0274841322 2.873267e-02
## racepctblack 0.1256003384 1.275931e-01 0.1296063557 1.316153e-01
## racePctWhite -0.0849268628 -8.479739e-02 -0.0845405451 -8.422446e-02
## racePctAsian -0.0200525389 -2.041723e-02 -0.0207560159 -2.101515e-02
## racePctHisp 0.0107794791 1.169205e-02 0.0126530542 1.365637e-02
## agePct12t21 -0.0046873181 -3.661365e-03 -0.0023369266 -1.075849e-03
## agePct12t29 -0.0741824402 -7.836406e-02 -0.0829800073 -8.754657e-02
## agePct16t24 -0.0135316291 -1.321612e-02 -0.0130225937 -1.275503e-02
## agePct65up 0.0226079863 2.363541e-02 0.0247654460 2.576758e-02
## numbUrban -0.0080694428 -9.654546e-03 -0.0113220668 -1.293534e-02
## pctUrban 0.0352419878 3.570606e-02 0.0361508118 3.657313e-02
## medIncome 0.0134718539 1.439880e-02 0.0154029570 1.641251e-02
## pctWWage -0.0341546348 -3.623373e-02 -0.0386754590 -4.110912e-02
## pctWFarmSelf 0.0110255261 1.227027e-02 0.0135239739 1.474070e-02
## pctWInvInc -0.0731881943 -7.566175e-02 -0.0783456412 -8.105970e-02
## pctWSocSec 0.0225029370 2.358867e-02 0.0248577291 2.609496e-02
## pctWPubAsst 0.0096283421 9.139920e-03 0.0087482521 8.336508e-03
## pctWRetire -0.0522160182 -5.403513e-02 -0.0558148781 -5.752050e-02
## medFamInc 0.0076469817 8.722266e-03 0.0099340813 1.111835e-02
## perCapInc -0.0068205950 -7.762510e-03 -0.0087848174 -9.805555e-03
## whitePerCap -0.0062591042 -9.366618e-03 -0.0129413092 -1.657178e-02
## blackPerCap -0.0227945812 -2.300399e-02 -0.0232503483 -2.346965e-02
## indianPerCap -0.0224678631 -2.289522e-02 -0.0233091018 -2.369228e-02
## AsianPerCap 0.0229525275 2.312276e-02 0.0232737953 2.342284e-02
## OtherPerCap 0.0370226360 3.757694e-02 0.0380922430 3.858989e-02
## HispPerCap 0.0202899054 2.060824e-02 0.0209241653 2.123658e-02
## NumUnderPov 0.0029381825 2.761692e-03 0.0028574072 3.139416e-03
## PctPopUnderPov -0.0389403587 -4.263668e-02 -0.0465356848 -5.038656e-02
## PctLess9thGrade -0.0295956288 -3.172631e-02 -0.0340421241 -3.622341e-02
## PctNotHSGrad 0.0172876961 1.739362e-02 0.0173802884 1.754942e-02
## PctBSorMore -0.0004607353 4.507534e-04 0.0016054696 2.789433e-03
## PctUnemployed -0.0240757010 -2.512214e-02 -0.0261911751 -2.706657e-02
## PctEmploy 0.0353313383 3.880404e-02 0.0427796419 4.673633e-02
## PctEmplManu -0.0256265514 -2.630275e-02 -0.0269778877 -2.770037e-02
## PctEmplProfServ -0.0052468107 -5.039007e-03 -0.0049124533 -4.787052e-03
## PctOccupManu 0.0173878331 1.876108e-02 0.0201632292 2.161372e-02
## PctOccupMgmtProf 0.0007450139 1.710160e-03 0.0028495244 4.112236e-03
## MalePctDivorce 0.0738342861 7.638705e-02 0.0791655915 8.207433e-02
## MalePctNevMarr 0.0510318758 5.336128e-02 0.0558067901 5.832653e-02
## FemalePctDiv -0.0096014630 -1.311217e-02 -0.0168432928 -2.061274e-02
## TotalPctDiv 0.0230039283 2.188428e-02 0.0205724367 1.934124e-02
## PersPerFam 0.0256718003 2.617179e-02 0.0267908050 2.726137e-02
## PctFam2Par -0.0721739830 -7.271628e-02 -0.0732538421 -7.371855e-02
## PctKids2Par -0.0970517124 -9.881681e-02 -0.1008409999 -1.027881e-01
## PctYoungKids2Par -0.0586862866 -5.860937e-02 -0.0585286837 -5.837007e-02
## PctTeen2Par -0.0415465968 -4.007551e-02 -0.0385803954 -3.711393e-02
## PctWorkMomYoungKids -0.0043518826 -3.906319e-03 -0.0032503274 -2.575269e-03
## PctWorkMom -0.0676971052 -7.093345e-02 -0.0743881852 -7.780653e-02
## NumIlleg 0.0033386187 -3.313714e-04 -0.0043291379 -8.214291e-03
## PctIlleg 0.1268989444 1.287451e-01 0.1304806797 1.321320e-01
## NumImmig -0.0644815232 -6.686769e-02 -0.0693717801 -7.171570e-02
## PctImmigRecent 0.0065901642 7.224108e-03 0.0078744299 8.548111e-03
## PctImmigRec5 -0.0130392748 -1.353842e-02 -0.0139871800 -1.444210e-02
## PctImmigRec8 -0.0084589864 -8.908340e-03 -0.0093453373 -9.756011e-03
## PctImmigRec10 0.0064518439 6.355753e-03 0.0062541042 6.156551e-03
## PctRecentImmig 0.0000491509 -4.773210e-04 -0.0011132947 -1.799628e-03
## PctRecImmig5 0.0061615652 5.936139e-03 0.0056593508 5.339423e-03
## PctRecImmig8 0.0187369513 1.941919e-02 0.0201841731 2.093704e-02
## PctRecImmig10 0.0224155096 2.309571e-02 0.0238510923 2.456429e-02
## PctSpeakEnglOnly 0.0011275236 8.473289e-04 0.0004043650 3.406593e-05
## PctNotSpeakEnglWell -0.0159662497 -1.718277e-02 -0.0185210438 -1.988191e-02
## PctLargHouseFam 0.0030117651 1.213114e-03 -0.0007542696 -2.670170e-03
## PctLargHouseOccup -0.0054937768 -7.267192e-03 -0.0092776829 -1.122783e-02
## PersPerOccupHous 0.0370488000 3.983810e-02 0.0429709371 4.616969e-02
## PersPerOwnOccHous -0.0276995177 -2.906708e-02 -0.0304735069 -3.196125e-02
## PersPerRentOccHous 0.0055909399 4.704008e-03 0.0036894573 2.659377e-03
## PctPersOwnOccup -0.0342123062 -3.598044e-02 -0.0379307290 -3.989682e-02
## PctPersDenseHous 0.0547325767 5.711889e-02 0.0597101484 6.236092e-02
## PctHousLess3BR 0.0310935070 3.203005e-02 0.0330827573 3.408154e-02
## MedNumBR 0.0018411875 2.153531e-03 0.0024832869 2.829833e-03
## HousVacant 0.0948423431 9.785725e-02 0.1008777945 1.038888e-01
## PctHousOccup -0.0628855441 -6.336517e-02 -0.0637423282 -6.404939e-02
## PctHousOwnOcc -0.0046530435 -4.344182e-03 -0.0041350271 -3.795358e-03
## PctVacantBoarded 0.0561528007 5.648321e-02 0.0568345647 5.712039e-02
## PctVacMore6Mos -0.0341209171 -3.546421e-02 -0.0368115572 -3.813621e-02
## MedYrHousBuilt -0.0005120525 -1.230782e-03 -0.0019053346 -2.606615e-03
## PctHousNoPhone 0.0204675147 2.062597e-02 0.0208961438 2.108154e-02
## PctWOFullPlumb -0.0050807259 -5.378742e-03 -0.0056570403 -5.931017e-03
## OwnOccLowQuart -0.0269579413 -2.854629e-02 -0.0303210978 -3.209955e-02
## OwnOccMedVal -0.0084807493 -8.672420e-03 -0.0088876138 -9.039135e-03
## OwnOccHiQuart -0.0001777473 -4.910865e-05 0.0001466103 3.913449e-04
## RentLowQ -0.0591344971 -6.308278e-02 -0.0674029974 -7.169670e-02
## RentMedian 0.0078918697 8.586207e-03 0.0092197329 9.931009e-03
## RentHighQ 0.0179020018 1.897003e-02 0.0201320944 2.121692e-02
## MedRent 0.0366549353 3.917262e-02 0.0420966078 4.503548e-02
## MedRentPctHousInc 0.0409632523 4.193283e-02 0.0429316360 4.386534e-02
## MedOwnCostPctInc -0.0129359414 -1.396900e-02 -0.0149934809 -1.602130e-02
## MedOwnCostPctIncNoMtg -0.0531819543 -5.453055e-02 -0.0558667071 -5.712000e-02
## NumInShelters 0.0772000863 7.900717e-02 0.0808968024 8.267047e-02
## NumStreet 0.1577831928 1.606689e-01 0.1634493970 1.660275e-01
## PctForeignBorn 0.0208988110 2.186891e-02 0.0229118172 2.397021e-02
## PctBornSameState -0.0058776254 -5.420681e-03 -0.0049722724 -4.545697e-03
## PctSameHouse85 0.0113041405 1.153707e-02 0.0117669695 1.194684e-02
## PctSameCity85 0.0282333407 2.855919e-02 0.0288586527 2.913340e-02
## PctSameState85 0.0020454757 2.167425e-03 0.0023353027 2.480443e-03
## LandArea 0.0252413203 2.547078e-02 0.0257464927 2.592225e-02
## PopDens 0.0041097939 3.698029e-03 0.0032927263 2.880115e-03
## PctUsePubTrans -0.0104343798 -1.148062e-02 -0.0125203031 -1.355378e-02
##
## (Intercept) 0.4964499039 0.5019202776 0.5075149862 0.5125508572
## (Intercept) . . . .
## state -0.0008618282 -0.0008632560 -0.0008642304 -0.0008648032
## fold -0.0016503432 -0.0016636371 -0.0016759491 -0.0016873858
## population -0.0206046981 -0.0219273191 -0.0231209089 -0.0242602478
## householdsize 0.0299102252 0.0310494504 0.0322669160 0.0333573713
## racepctblack 0.1335989909 0.1355698071 0.1376014533 0.1396355055
## racePctWhite -0.0837876930 -0.0832222498 -0.0825173965 -0.0817828411
## racePctAsian -0.0212267092 -0.0213847563 -0.0214881676 -0.0215143944
## racePctHisp 0.0146988271 0.0157516126 0.0168174332 0.0179066884
## agePct12t21 0.0001912722 0.0015337734 0.0031961048 0.0048269641
## agePct12t29 -0.0923982012 -0.0975200738 -0.1031129132 -0.1085847278
## agePct16t24 -0.0124224259 -0.0120848524 -0.0118932191 -0.0116699274
## agePct65up 0.0267617948 0.0277567656 0.0288115510 0.0297517514
## numbUrban -0.0145196410 -0.0161062017 -0.0178144933 -0.0194976863
## pctUrban 0.0369797474 0.0373689407 0.0377407045 0.0380904850
## medIncome 0.0174092381 0.0184275376 0.0195740344 0.0207028787
## pctWWage -0.0436278615 -0.0462721563 -0.0492845199 -0.0522826781
## pctWFarmSelf 0.0159489217 0.0171457213 0.0183397313 0.0194839826
## pctWInvInc -0.0837920582 -0.0865370845 -0.0894534389 -0.0923604052
## pctWSocSec 0.0272601229 0.0283904223 0.0296804307 0.0309367071
## pctWPubAsst 0.0079028252 0.0074303373 0.0070139825 0.0065832882
## pctWRetire -0.0592161202 -0.0608700745 -0.0624429035 -0.0639100464
## medFamInc 0.0123355375 0.0136395967 0.0151978813 0.0167989332
## perCapInc -0.0108986581 -0.0120358690 -0.0131756151 -0.0142201094
## whitePerCap -0.0203740363 -0.0243880325 -0.0289301830 -0.0334932967
## blackPerCap -0.0236759340 -0.0238757416 -0.0241193307 -0.0243307138
## indianPerCap -0.0240499240 -0.0243856965 -0.0247114940 -0.0250096919
## AsianPerCap 0.0235625283 0.0236932907 0.0238087704 0.0239275363
## OtherPerCap 0.0390647889 0.0395154638 0.0399337070 0.0403378831
## HispPerCap 0.0215623687 0.0218999139 0.0222330505 0.0225632954
## NumUnderPov 0.0036127386 0.0043062087 0.0053254370 0.0064836175
## PctPopUnderPov -0.0543315946 -0.0583710068 -0.0625959635 -0.0667410415
## PctLess9thGrade -0.0384319045 -0.0406744247 -0.0430952512 -0.0453765629
## PctNotHSGrad 0.0178160533 0.0181273763 0.0183687224 0.0187636697
## PctBSorMore 0.0040551477 0.0054384154 0.0070589575 0.0086864716
## PctUnemployed -0.0277664295 -0.0283409829 -0.0288977810 -0.0292767408
## PctEmploy 0.0507389019 0.0548605476 0.0595094382 0.0641492566
## PctEmplManu -0.0284789155 -0.0293020226 -0.0301305190 -0.0309887897
## PctEmplProfServ -0.0046429387 -0.0045040921 -0.0044817946 -0.0044927170
## PctOccupManu 0.0231848608 0.0248444097 0.0265331450 0.0282338366
## PctOccupMgmtProf 0.0054345220 0.0068172788 0.0084084188 0.0101103195
## MalePctDivorce 0.0850706184 0.0881613392 0.0914938878 0.0949164074
## MalePctNevMarr 0.0609988588 0.0637907623 0.0667366881 0.0697220731
## FemalePctDiv -0.0244660879 -0.0284209369 -0.0325896265 -0.0367502051
## TotalPctDiv 0.0181368687 0.0169252419 0.0154887945 0.0141068139
## PersPerFam 0.0277490363 0.0282577719 0.0288030509 0.0291537695
## PctFam2Par -0.0742989196 -0.0749621765 -0.0755598505 -0.0760165977
## PctKids2Par -0.1047969527 -0.1069319341 -0.1093391174 -0.1116531207
## PctYoungKids2Par -0.0581372506 -0.0578610231 -0.0575645612 -0.0571982281
## PctTeen2Par -0.0356300753 -0.0341523869 -0.0326949369 -0.0313009339
## PctWorkMomYoungKids -0.0018045940 -0.0009272338 0.0001704239 0.0012723594
## PctWorkMom -0.0812788095 -0.0848262625 -0.0885925054 -0.0922798101
## NumIlleg -0.0121864048 -0.0162361361 -0.0205576550 -0.0247437158
## PctIlleg 0.1336948156 0.1351492905 0.1364557220 0.1376662665
## NumImmig -0.0739226912 -0.0760556423 -0.0782830525 -0.0803752154
## PctImmigRecent 0.0092262889 0.0099132117 0.0106112199 0.0113092820
## PctImmigRec5 -0.0148857797 -0.0153143016 -0.0156716366 -0.0160135209
## PctImmigRec8 -0.0101381159 -0.0105042364 -0.0108548572 -0.0111744670
## PctImmigRec10 0.0060842529 0.0060263064 0.0059549236 0.0058737554
## PctRecentImmig -0.0025130337 -0.0032817231 -0.0041838466 -0.0051219481
## PctRecImmig5 0.0049994996 0.0046372492 0.0041792976 0.0036730889
## PctRecImmig8 0.0217176812 0.0225414576 0.0234453056 0.0243269534
## PctRecImmig10 0.0252566080 0.0259443239 0.0266932822 0.0273830418
## PctSpeakEnglOnly -0.0003447081 -0.0007789766 -0.0013817572 -0.0019040116
## PctNotSpeakEnglWell -0.0213498380 -0.0229003001 -0.0245866835 -0.0262891069
## PctLargHouseFam -0.0046412280 -0.0066651001 -0.0088110911 -0.0108622908
## PctLargHouseOccup -0.0131592446 -0.0150993410 -0.0172228263 -0.0192561019
## PersPerOccupHous 0.0495768861 0.0532044387 0.0572666437 0.0614284531
## PersPerOwnOccHous -0.0335486235 -0.0352239618 -0.0369977130 -0.0388507891
## PersPerRentOccHous 0.0015483477 0.0003518920 -0.0009977493 -0.0023445742
## PctPersOwnOccup -0.0420210008 -0.0443188177 -0.0468945963 -0.0494673327
## PctPersDenseHous 0.0651393415 0.0680646008 0.0712578471 0.0744905257
## PctHousLess3BR 0.0350558060 0.0360455645 0.0372055024 0.0383287555
## MedNumBR 0.0031940589 0.0035770859 0.0039792233 0.0043900501
## HousVacant 0.1069354590 0.1099811500 0.1130229780 0.1160093705
## PctHousOccup -0.0642777159 -0.0644171722 -0.0644537290 -0.0644401677
## PctHousOwnOcc -0.0033487938 -0.0028391693 -0.0024097887 -0.0019068510
## PctVacantBoarded 0.0573808312 0.0576218520 0.0578832476 0.0580944795
## PctVacMore6Mos -0.0394350601 -0.0407044563 -0.0419697952 -0.0432031033
## MedYrHousBuilt -0.0032698291 -0.0038976495 -0.0044790056 -0.0050858251
## PctHousNoPhone 0.0212699944 0.0214936465 0.0218273687 0.0220952873
## PctWOFullPlumb -0.0061972958 -0.0064482314 -0.0066818065 -0.0069067357
## OwnOccLowQuart -0.0339776832 -0.0360110159 -0.0382845381 -0.0405648538
## OwnOccMedVal -0.0091218250 -0.0091724101 -0.0092523289 -0.0092772326
## OwnOccHiQuart 0.0007168680 0.0011184622 0.0016098250 0.0021395842
## RentLowQ -0.0760846401 -0.0806078847 -0.0855292479 -0.0903742113
## RentMedian 0.0107643103 0.0116683678 0.0124399166 0.0132010455
## RentHighQ 0.0223241477 0.0234534466 0.0245998225 0.0255751589
## MedRent 0.0480747073 0.0512725914 0.0549453767 0.0586361941
## MedRentPctHousInc 0.0447340373 0.0455604135 0.0464303599 0.0472712189
## MedOwnCostPctInc -0.0170839672 -0.0181467101 -0.0191770754 -0.0201829153
## MedOwnCostPctIncNoMtg -0.0583187910 -0.0594709075 -0.0606075898 -0.0616591344
## NumInShelters 0.0843976159 0.0860780706 0.0878241412 0.0894793018
## NumStreet 0.1684213612 0.1706476437 0.1727502734 0.1746737146
## PctForeignBorn 0.0250235357 0.0260779489 0.0272242788 0.0284051929
## PctBornSameState -0.0041174426 -0.0036795733 -0.0032556120 -0.0028632297
## PctSameHouse85 0.0121262282 0.0123051390 0.0124791535 0.0125787732
## PctSameCity85 0.0293684294 0.0295645418 0.0297326139 0.0298893095
## PctSameState85 0.0025999721 0.0027123932 0.0028913944 0.0030719327
## LandArea 0.0260780646 0.0262119145 0.0263607588 0.0264227641
## PopDens 0.0024507745 0.0020058668 0.0015699396 0.0011476657
## PctUsePubTrans -0.0145889960 -0.0156251270 -0.0166579305 -0.0176715338ridge.mod$lambda## [1] 171.99845173 156.71858334 142.79613634 130.11052116 118.55186107
## [6] 108.02004049 98.42383782 89.68013534 81.71319929 74.45402388
## [11] 67.83973361 61.81303866 56.32173867 51.31827064 46.75929692
## [16] 42.60532986 38.82038978 35.37169335 32.22936961 29.36620124
## [21] 26.75738886 24.38033618 22.21445431 20.24098342 18.44283024
## [26] 16.80442003 15.31156167 13.95132474 12.71192750 11.58263490
## [31] 10.55366554 9.61610698 8.76183854 7.98346095 7.27423229
## [36] 6.62800954 6.03919544 5.50268996 5.01384615 4.56842988
## [41] 4.16258316 3.79279074 3.45584967 3.14884151 2.86910711
## [46] 2.61422354 2.38198313 2.17037431 1.97756424 1.80188288
## [51] 1.64180857 1.49595483 1.36305832 1.24196798 1.13163497
## [56] 1.03110363 0.93950323 0.85604035 0.77999209 0.71069974
## [61] 0.64756313 0.59003541 0.53761829 0.48985776 0.44634015
## [66] 0.40668852 0.37055943 0.33763995 0.30764495 0.28031462
## [71] 0.25541224 0.23272212 0.21204773 0.19321000 0.17604575
## [76] 0.16040633 0.14615628 0.13317216 0.12134151 0.11056186
## [81] 0.10073985 0.09179040 0.08363599 0.07620600 0.06943607
## [86] 0.06326756 0.05764705 0.05252584 0.04785959 0.04360788
## [91] 0.03973387 0.03620403 0.03298776 0.03005722 0.02738702
## [96] 0.02495403 0.02273718 0.02071727 0.01887681 0.01719985plot(ridge.mod,"lambda", label=TRUE)
ridge.mod$lambda[5]## [1] 118.5519log(ridge.mod$lambda[5])## [1] 4.775351coef(ridge.mod)[,5] # Lambda más grande penaliza más tienden a ser los beta más pequeños## (Intercept) (Intercept) state
## 2.408608e-01 0.000000e+00 -5.809497e-06
## fold population householdsize
## -5.026316e-06 1.277161e-03 -9.759961e-05
## racepctblack racePctWhite racePctAsian
## 1.107236e-03 -1.242253e-03 8.393138e-05
## racePctHisp agePct12t21 agePct12t29
## 5.486080e-04 1.552188e-04 4.517798e-04
## agePct16t24 agePct65up numbUrban
## 2.476580e-04 1.645788e-04 1.251180e-03
## pctUrban medIncome pctWWage
## 8.780469e-05 -8.753072e-04 -7.284557e-04
## pctWFarmSelf pctWInvInc pctWSocSec
## -3.371917e-04 -1.414723e-03 2.944539e-04
## pctWPubAsst pctWRetire medFamInc
## 1.131630e-03 -2.578268e-04 -9.579953e-04
## perCapInc whitePerCap blackPerCap
## -7.914889e-04 -4.703871e-04 -6.929404e-04
## indianPerCap AsianPerCap OtherPerCap
## -2.352204e-04 -3.374829e-04 -2.782774e-04
## HispPerCap NumUnderPov PctPopUnderPov
## -5.699369e-04 1.540775e-03 9.945026e-04
## PctLess9thGrade PctNotHSGrad PctBSorMore
## 8.358293e-04 1.039578e-03 -6.504941e-04
## PctUnemployed PctEmploy PctEmplManu
## 1.087290e-03 -8.275196e-04 -1.028824e-04
## PctEmplProfServ PctOccupManu PctOccupMgmtProf
## -1.783911e-04 6.407005e-04 -7.858235e-04
## MalePctDivorce MalePctNevMarr FemalePctDiv
## 1.268924e-03 7.606498e-04 1.397903e-03
## TotalPctDiv PersPerFam PctFam2Par
## 1.326163e-03 3.984205e-04 -1.539690e-03
## PctKids2Par PctYoungKids2Par PctTeen2Par
## -1.575876e-03 -1.338781e-03 -1.522440e-03
## PctWorkMomYoungKids PctWorkMom NumIlleg
## -5.901190e-05 -3.782991e-04 1.915348e-03
## PctIlleg NumImmig PctImmigRecent
## 1.418760e-03 1.483465e-03 3.398310e-04
## PctImmigRec5 PctImmigRec8 PctImmigRec10
## 4.446755e-04 5.368248e-04 6.532797e-04
## PctRecentImmig PctRecImmig5 PctRecImmig8
## 4.293147e-04 4.608521e-04 4.704452e-04
## PctRecImmig10 PctSpeakEnglOnly PctNotSpeakEnglWell
## 4.952038e-04 -4.644079e-04 5.949591e-04
## PctLargHouseFam PctLargHouseOccup PersPerOccupHous
## 8.552199e-04 6.766766e-04 -1.021186e-04
## PersPerOwnOccHous PersPerRentOccHous PctPersOwnOccup
## -3.469782e-04 5.738387e-04 -1.164554e-03
## PctPersDenseHous PctHousLess3BR MedNumBR
## 9.447383e-04 1.201214e-03 -6.101935e-04
## HousVacant PctHousOccup PctHousOwnOcc
## 1.239583e-03 -7.251163e-04 -1.108661e-03
## PctVacantBoarded PctVacMore6Mos MedYrHousBuilt
## 9.785901e-04 4.547703e-05 -2.051449e-04
## PctHousNoPhone PctWOFullPlumb OwnOccLowQuart
## 8.773115e-04 7.700253e-04 -4.006782e-04
## OwnOccMedVal OwnOccHiQuart RentLowQ
## -3.502443e-04 -3.094050e-04 -4.929996e-04
## RentMedian RentHighQ MedRent
## -4.907352e-04 -3.989263e-04 -4.787833e-04
## MedRentPctHousInc MedOwnCostPctInc MedOwnCostPctIncNoMtg
## 8.430518e-04 1.587122e-04 1.221550e-04
## NumInShelters NumStreet PctForeignBorn
## 1.618177e-03 1.501186e-03 3.717099e-04
## PctBornSameState PctSameHouse85 PctSameCity85
## -1.728715e-04 -3.705701e-04 1.697735e-04
## PctSameState85 LandArea PopDens
## -4.433635e-05 7.964360e-04 6.103165e-04
## PctUsePubTrans
## 3.023410e-04plot(ridge.mod,"lambda", label=TRUE)
abline(v = log(ridge.mod$lambda[5]), col="blue", lwd=4, lty=3)
log(ridge.mod$lambda[70])## [1] -1.271843coef(ridge.mod)[,70] # Lambda más grande penaliza más tienden a ser los beta más pequeños## (Intercept) (Intercept) state
## 3.297768e-01 0.000000e+00 -5.472795e-04
## fold population householdsize
## -7.497081e-04 1.871996e-02 1.720520e-03
## racepctblack racePctWhite racePctAsian
## 7.665504e-02 -6.563081e-02 -3.969969e-03
## racePctHisp agePct12t21 agePct12t29
## 3.795609e-03 -1.305775e-02 -2.168276e-02
## agePct16t24 agePct65up numbUrban
## -1.430345e-02 6.453711e-03 2.367583e-02
## pctUrban medIncome pctWWage
## 1.906802e-02 -2.247983e-03 -1.479235e-02
## pctWFarmSelf pctWInvInc pctWSocSec
## -1.242855e-02 -4.082123e-02 6.320126e-03
## pctWPubAsst pctWRetire medFamInc
## 2.252459e-02 -1.576393e-02 -6.102173e-03
## perCapInc whitePerCap blackPerCap
## 4.657242e-04 1.748806e-02 -1.272751e-02
## indianPerCap AsianPerCap OtherPerCap
## -7.070248e-03 1.377703e-02 1.804893e-02
## HispPerCap NumUnderPov PctPopUnderPov
## 1.194161e-02 2.703722e-02 1.057418e-02
## PctLess9thGrade PctNotHSGrad PctBSorMore
## 3.032582e-03 1.848870e-02 -5.999242e-03
## PctUnemployed PctEmploy PctEmplManu
## 9.339117e-03 -6.589839e-03 -1.434873e-02
## PctEmplProfServ PctOccupManu PctOccupMgmtProf
## -5.967509e-03 3.306342e-03 -4.680411e-03
## MalePctDivorce MalePctNevMarr FemalePctDiv
## 4.551428e-02 2.036452e-02 3.723954e-02
## TotalPctDiv PersPerFam PctFam2Par
## 4.000917e-02 1.535591e-02 -5.687271e-02
## PctKids2Par PctYoungKids2Par PctTeen2Par
## -6.413976e-02 -4.869122e-02 -5.546508e-02
## PctWorkMomYoungKids PctWorkMom NumIlleg
## -7.914507e-05 -1.853212e-02 5.122660e-02
## PctIlleg NumImmig PctImmigRecent
## 7.553013e-02 -3.612684e-03 2.062392e-04
## PctImmigRec5 PctImmigRec8 PctImmigRec10
## -1.226401e-03 3.278973e-03 9.747493e-03
## PctRecentImmig PctRecImmig5 PctRecImmig8
## 3.543828e-03 5.846424e-03 8.704961e-03
## PctRecImmig10 PctSpeakEnglOnly PctNotSpeakEnglWell
## 1.052167e-02 2.634126e-04 4.290006e-05
## PctLargHouseFam PctLargHouseOccup PersPerOccupHous
## 2.215884e-02 1.620209e-02 7.399569e-03
## PersPerOwnOccHous PersPerRentOccHous PctPersOwnOccup
## -1.164483e-02 1.583568e-02 -1.871081e-02
## PctPersDenseHous PctHousLess3BR MedNumBR
## 2.614299e-02 1.849316e-02 -3.591169e-03
## HousVacant PctHousOccup PctHousOwnOcc
## 4.765482e-02 -3.759136e-02 -1.097143e-02
## PctVacantBoarded PctVacMore6Mos MedYrHousBuilt
## 4.263753e-02 -8.488120e-03 6.287736e-03
## PctHousNoPhone PctWOFullPlumb OwnOccLowQuart
## 2.002779e-02 6.246714e-03 -5.641226e-03
## OwnOccMedVal OwnOccHiQuart RentLowQ
## -1.649954e-03 1.638952e-03 -1.027964e-02
## RentMedian RentHighQ MedRent
## 8.802502e-04 2.774674e-03 7.142587e-03
## MedRentPctHousInc MedOwnCostPctInc MedOwnCostPctIncNoMtg
## 2.452740e-02 5.472063e-03 -1.529272e-02
## NumInShelters NumStreet PctForeignBorn
## 4.693200e-02 7.444839e-02 8.125758e-03
## PctBornSameState PctSameHouse85 PctSameCity85
## -1.155977e-02 2.406200e-03 1.647930e-02
## PctSameState85 LandArea PopDens
## -7.922816e-04 2.077187e-02 1.021178e-02
## PctUsePubTrans
## 7.968234e-03plot(ridge.mod,"lambda", label=TRUE)
abline(v = log(ridge.mod$lambda[70]), col="blue", lwd=4, lty=3)
datosx<-model.matrix(ViolentCrimesPerPop~.,datos)[,-c(103)]
pred<-predict(ridge.mod,s=ridge.mod$lambda[5],newx=datosx)
# Medición de precisión
numero.predictoras <- dim(datosx)[2]-1
pre.ridge <- indices.precision(datos$ViolentCrimesPerPop,pred,numero.predictoras)
pre.ridge## $error.cuadratico
## [1] 0.0518556
##
## $raiz.error.cuadratico
## [1] 0.233776
##
## $error.relativo
## [1] 0.730497
##
## $correlacion
## [1] 0.7288325pred<-predict(ridge.mod,s=ridge.mod$lambda[70],newx=datosx)
# Medición de precisión
numero.predictoras <- dim(datosx)[2]-1
pre.ridge <- indices.precision(datos$ViolentCrimesPerPop,pred,numero.predictoras)
pre.ridge## $error.cuadratico
## [1] 0.01917118
##
## $raiz.error.cuadratico
## [1] 0.1421433
##
## $error.relativo
## [1] 0.4074684
##
## $correlacion
## [1] 0.8078744# Usando validación cruzada para determinar el mejor Lambda
sal.cv<-cv.glmnet(x,y,alpha=0)
plot(sal.cv)
mejor.lambda<-sal.cv$lambda.min
mejor.lambda## [1] 0.01719985log(mejor.lambda)## [1] -4.062855coef(ridge.mod)[,which(ridge.mod$lambda==mejor.lambda)]## (Intercept) (Intercept) state
## 0.5125508572 0.0000000000 -0.0008648032
## fold population householdsize
## -0.0016873858 -0.0242602478 0.0333573713
## racepctblack racePctWhite racePctAsian
## 0.1396355055 -0.0817828411 -0.0215143944
## racePctHisp agePct12t21 agePct12t29
## 0.0179066884 0.0048269641 -0.1085847278
## agePct16t24 agePct65up numbUrban
## -0.0116699274 0.0297517514 -0.0194976863
## pctUrban medIncome pctWWage
## 0.0380904850 0.0207028787 -0.0522826781
## pctWFarmSelf pctWInvInc pctWSocSec
## 0.0194839826 -0.0923604052 0.0309367071
## pctWPubAsst pctWRetire medFamInc
## 0.0065832882 -0.0639100464 0.0167989332
## perCapInc whitePerCap blackPerCap
## -0.0142201094 -0.0334932967 -0.0243307138
## indianPerCap AsianPerCap OtherPerCap
## -0.0250096919 0.0239275363 0.0403378831
## HispPerCap NumUnderPov PctPopUnderPov
## 0.0225632954 0.0064836175 -0.0667410415
## PctLess9thGrade PctNotHSGrad PctBSorMore
## -0.0453765629 0.0187636697 0.0086864716
## PctUnemployed PctEmploy PctEmplManu
## -0.0292767408 0.0641492566 -0.0309887897
## PctEmplProfServ PctOccupManu PctOccupMgmtProf
## -0.0044927170 0.0282338366 0.0101103195
## MalePctDivorce MalePctNevMarr FemalePctDiv
## 0.0949164074 0.0697220731 -0.0367502051
## TotalPctDiv PersPerFam PctFam2Par
## 0.0141068139 0.0291537695 -0.0760165977
## PctKids2Par PctYoungKids2Par PctTeen2Par
## -0.1116531207 -0.0571982281 -0.0313009339
## PctWorkMomYoungKids PctWorkMom NumIlleg
## 0.0012723594 -0.0922798101 -0.0247437158
## PctIlleg NumImmig PctImmigRecent
## 0.1376662665 -0.0803752154 0.0113092820
## PctImmigRec5 PctImmigRec8 PctImmigRec10
## -0.0160135209 -0.0111744670 0.0058737554
## PctRecentImmig PctRecImmig5 PctRecImmig8
## -0.0051219481 0.0036730889 0.0243269534
## PctRecImmig10 PctSpeakEnglOnly PctNotSpeakEnglWell
## 0.0273830418 -0.0019040116 -0.0262891069
## PctLargHouseFam PctLargHouseOccup PersPerOccupHous
## -0.0108622908 -0.0192561019 0.0614284531
## PersPerOwnOccHous PersPerRentOccHous PctPersOwnOccup
## -0.0388507891 -0.0023445742 -0.0494673327
## PctPersDenseHous PctHousLess3BR MedNumBR
## 0.0744905257 0.0383287555 0.0043900501
## HousVacant PctHousOccup PctHousOwnOcc
## 0.1160093705 -0.0644401677 -0.0019068510
## PctVacantBoarded PctVacMore6Mos MedYrHousBuilt
## 0.0580944795 -0.0432031033 -0.0050858251
## PctHousNoPhone PctWOFullPlumb OwnOccLowQuart
## 0.0220952873 -0.0069067357 -0.0405648538
## OwnOccMedVal OwnOccHiQuart RentLowQ
## -0.0092772326 0.0021395842 -0.0903742113
## RentMedian RentHighQ MedRent
## 0.0132010455 0.0255751589 0.0586361941
## MedRentPctHousInc MedOwnCostPctInc MedOwnCostPctIncNoMtg
## 0.0472712189 -0.0201829153 -0.0616591344
## NumInShelters NumStreet PctForeignBorn
## 0.0894793018 0.1746737146 0.0284051929
## PctBornSameState PctSameHouse85 PctSameCity85
## -0.0028632297 0.0125787732 0.0298893095
## PctSameState85 LandArea PopDens
## 0.0030719327 0.0264227641 0.0011476657
## PctUsePubTrans
## -0.0176715338plot(ridge.mod,"lambda", label=TRUE)
abline(v = log(mejor.lambda), col="blue", lwd=4, lty=3)
pred<-predict(ridge.mod,s=mejor.lambda,newx=datosx)
# Medición de precisión
numero.predictoras <- dim(datosx)[2]-1
pre.ridge <- indices.precision(datos$ViolentCrimesPerPop,pred,numero.predictoras)
pre.ridge## $error.cuadratico
## [1] 0.01720385
##
## $raiz.error.cuadratico
## [1] 0.1346526
##
## $error.relativo
## [1] 0.3845009
##
## $correlacion
## [1] 0.8265301###LASSO
# Debemos eliminar la columna 1
x<-model.matrix(ViolentCrimesPerPop~.,datos)[,-c(103)]
head(x)## (Intercept) state fold population householdsize racepctblack racePctWhite
## 1 1 8 1 0.19 0.33 0.02 0.90
## 2 1 53 1 0.00 0.16 0.12 0.74
## 3 1 24 1 0.00 0.42 0.49 0.56
## 4 1 34 1 0.04 0.77 1.00 0.08
## 5 1 42 1 0.01 0.55 0.02 0.95
## 6 1 6 1 0.02 0.28 0.06 0.54
## racePctAsian racePctHisp agePct12t21 agePct12t29 agePct16t24 agePct65up
## 1 0.12 0.17 0.34 0.47 0.29 0.32
## 2 0.45 0.07 0.26 0.59 0.35 0.27
## 3 0.17 0.04 0.39 0.47 0.28 0.32
## 4 0.12 0.10 0.51 0.50 0.34 0.21
## 5 0.09 0.05 0.38 0.38 0.23 0.36
## 6 1.00 0.25 0.31 0.48 0.27 0.37
## numbUrban pctUrban medIncome pctWWage pctWFarmSelf pctWInvInc pctWSocSec
## 1 0.20 1.0 0.37 0.72 0.34 0.60 0.29
## 2 0.02 1.0 0.31 0.72 0.11 0.45 0.25
## 3 0.00 0.0 0.30 0.58 0.19 0.39 0.38
## 4 0.06 1.0 0.58 0.89 0.21 0.43 0.36
## 5 0.02 0.9 0.50 0.72 0.16 0.68 0.44
## 6 0.04 1.0 0.52 0.68 0.20 0.61 0.28
## pctWPubAsst pctWRetire medFamInc perCapInc whitePerCap blackPerCap
## 1 0.15 0.43 0.39 0.40 0.39 0.32
## 2 0.29 0.39 0.29 0.37 0.38 0.33
## 3 0.40 0.84 0.28 0.27 0.29 0.27
## 4 0.20 0.82 0.51 0.36 0.40 0.39
## 5 0.11 0.71 0.46 0.43 0.41 0.28
## 6 0.15 0.25 0.62 0.72 0.76 0.77
## indianPerCap AsianPerCap OtherPerCap HispPerCap NumUnderPov PctPopUnderPov
## 1 0.27 0.27 0.36 0.41 0.08 0.19
## 2 0.16 0.30 0.22 0.35 0.01 0.24
## 3 0.07 0.29 0.28 0.39 0.01 0.27
## 4 0.16 0.25 0.36 0.44 0.01 0.10
## 5 0.00 0.74 0.51 0.48 0.00 0.06
## 6 0.28 0.52 0.48 0.60 0.01 0.12
## PctLess9thGrade PctNotHSGrad PctBSorMore PctUnemployed PctEmploy PctEmplManu
## 1 0.10 0.18 0.48 0.27 0.68 0.23
## 2 0.14 0.24 0.30 0.27 0.73 0.57
## 3 0.27 0.43 0.19 0.36 0.58 0.32
## 4 0.09 0.25 0.31 0.33 0.71 0.36
## 5 0.25 0.30 0.33 0.12 0.65 0.67
## 6 0.13 0.12 0.80 0.10 0.65 0.19
## PctEmplProfServ PctOccupManu PctOccupMgmtProf MalePctDivorce MalePctNevMarr
## 1 0.41 0.25 0.52 0.68 0.40
## 2 0.15 0.42 0.36 1.00 0.63
## 3 0.29 0.49 0.32 0.63 0.41
## 4 0.45 0.37 0.39 0.34 0.45
## 5 0.38 0.42 0.46 0.22 0.27
## 6 0.77 0.06 0.91 0.49 0.57
## FemalePctDiv TotalPctDiv PersPerFam PctFam2Par PctKids2Par PctYoungKids2Par
## 1 0.75 0.75 0.35 0.55 0.59 0.61
## 2 0.91 1.00 0.29 0.43 0.47 0.60
## 3 0.71 0.70 0.45 0.42 0.44 0.43
## 4 0.49 0.44 0.75 0.65 0.54 0.83
## 5 0.20 0.21 0.51 0.91 0.91 0.89
## 6 0.61 0.58 0.44 0.62 0.69 0.87
## PctTeen2Par PctWorkMomYoungKids PctWorkMom NumIlleg PctIlleg NumImmig
## 1 0.56 0.74 0.76 0.04 0.14 0.03
## 2 0.39 0.46 0.53 0.00 0.24 0.01
## 3 0.43 0.71 0.67 0.01 0.46 0.00
## 4 0.65 0.85 0.86 0.03 0.33 0.02
## 5 0.85 0.40 0.60 0.00 0.06 0.00
## 6 0.53 0.30 0.43 0.00 0.11 0.04
## PctImmigRecent PctImmigRec5 PctImmigRec8 PctImmigRec10 PctRecentImmig
## 1 0.24 0.27 0.37 0.39 0.07
## 2 0.52 0.62 0.64 0.63 0.25
## 3 0.07 0.06 0.15 0.19 0.02
## 4 0.11 0.20 0.30 0.31 0.05
## 5 0.03 0.07 0.20 0.27 0.01
## 6 0.30 0.35 0.43 0.47 0.50
## PctRecImmig5 PctRecImmig8 PctRecImmig10 PctSpeakEnglOnly PctNotSpeakEnglWell
## 1 0.07 0.08 0.08 0.89 0.06
## 2 0.27 0.25 0.23 0.84 0.10
## 3 0.02 0.04 0.05 0.88 0.04
## 4 0.08 0.11 0.11 0.81 0.08
## 5 0.02 0.04 0.05 0.88 0.05
## 6 0.50 0.56 0.57 0.45 0.28
## PctLargHouseFam PctLargHouseOccup PersPerOccupHous PersPerOwnOccHous
## 1 0.14 0.13 0.33 0.39
## 2 0.16 0.10 0.17 0.29
## 3 0.20 0.20 0.46 0.52
## 4 0.56 0.62 0.85 0.77
## 5 0.16 0.19 0.59 0.60
## 6 0.25 0.19 0.29 0.53
## PersPerRentOccHous PctPersOwnOccup PctPersDenseHous PctHousLess3BR MedNumBR
## 1 0.28 0.55 0.09 0.51 0.5
## 2 0.17 0.26 0.20 0.82 0.0
## 3 0.43 0.42 0.15 0.51 0.5
## 4 1.00 0.94 0.12 0.01 0.5
## 5 0.37 0.89 0.02 0.19 0.5
## 6 0.18 0.39 0.26 0.73 0.0
## HousVacant PctHousOccup PctHousOwnOcc PctVacantBoarded PctVacMore6Mos
## 1 0.21 0.71 0.52 0.05 0.26
## 2 0.02 0.79 0.24 0.02 0.25
## 3 0.01 0.86 0.41 0.29 0.30
## 4 0.01 0.97 0.96 0.60 0.47
## 5 0.01 0.89 0.87 0.04 0.55
## 6 0.02 0.84 0.30 0.16 0.28
## MedYrHousBuilt PctHousNoPhone PctWOFullPlumb OwnOccLowQuart OwnOccMedVal
## 1 0.65 0.14 0.06 0.22 0.19
## 2 0.65 0.16 0.00 0.21 0.20
## 3 0.52 0.47 0.45 0.18 0.17
## 4 0.52 0.11 0.11 0.24 0.21
## 5 0.73 0.05 0.14 0.31 0.31
## 6 0.25 0.02 0.05 0.94 1.00
## OwnOccHiQuart RentLowQ RentMedian RentHighQ MedRent MedRentPctHousInc
## 1 0.18 0.36 0.35 0.38 0.34 0.38
## 2 0.21 0.42 0.38 0.40 0.37 0.29
## 3 0.16 0.27 0.29 0.27 0.31 0.48
## 4 0.19 0.75 0.70 0.77 0.89 0.63
## 5 0.30 0.40 0.36 0.38 0.38 0.22
## 6 1.00 0.67 0.63 0.68 0.62 0.47
## MedOwnCostPctInc MedOwnCostPctIncNoMtg NumInShelters NumStreet PctForeignBorn
## 1 0.46 0.25 0.04 0 0.12
## 2 0.32 0.18 0.00 0 0.21
## 3 0.39 0.28 0.00 0 0.14
## 4 0.51 0.47 0.00 0 0.19
## 5 0.51 0.21 0.00 0 0.11
## 6 0.59 0.11 0.00 0 0.70
## PctBornSameState PctSameHouse85 PctSameCity85 PctSameState85 LandArea PopDens
## 1 0.42 0.50 0.51 0.64 0.12 0.26
## 2 0.50 0.34 0.60 0.52 0.02 0.12
## 3 0.49 0.54 0.67 0.56 0.01 0.21
## 4 0.30 0.73 0.64 0.65 0.02 0.39
## 5 0.72 0.64 0.61 0.53 0.04 0.09
## 6 0.42 0.49 0.73 0.64 0.01 0.58
## PctUsePubTrans
## 1 0.20
## 2 0.45
## 3 0.02
## 4 0.28
## 5 0.02
## 6 0.10# La siguiente instrucción construye la variable a predecir
y<-datos$ViolentCrimesPerPoplibrary(glmnet)
lasso.mod<-glmnet(x,y,alpha=1)
dim(coef(lasso.mod))## [1] 103 100coef(lasso.mod)## 103 x 100 sparse Matrix of class "dgCMatrix"## [[ suppressing 100 column names 's0', 's1', 's2' ... ]]##
## (Intercept) 0.2379789 0.25591869 0.27024238 0.28325558 0.2951769
## (Intercept) . . . . .
## state . . . . .
## fold . . . . .
## population . . . . .
## householdsize . . . . .
## racepctblack . . . . .
## racePctWhite . . . . .
## racePctAsian . . . . .
## racePctHisp . . . . .
## agePct12t21 . . . . .
## agePct12t29 . . . . .
## agePct16t24 . . . . .
## agePct65up . . . . .
## numbUrban . . . . .
## pctUrban . . . . .
## medIncome . . . . .
## pctWWage . . . . .
## pctWFarmSelf . . . . .
## pctWInvInc . . . . .
## pctWSocSec . . . . .
## pctWPubAsst . . . . .
## pctWRetire . . . . .
## medFamInc . . . . .
## perCapInc . . . . .
## whitePerCap . . . . .
## blackPerCap . . . . .
## indianPerCap . . . . .
## AsianPerCap . . . . .
## OtherPerCap . . . . .
## HispPerCap . . . . .
## NumUnderPov . . . . .
## PctPopUnderPov . . . . .
## PctLess9thGrade . . . . .
## PctNotHSGrad . . . . .
## PctBSorMore . . . . .
## PctUnemployed . . . . .
## PctEmploy . . . . .
## PctEmplManu . . . . .
## PctEmplProfServ . . . . .
## PctOccupManu . . . . .
## PctOccupMgmtProf . . . . .
## MalePctDivorce . . . . .
## MalePctNevMarr . . . . .
## FemalePctDiv . . . . .
## TotalPctDiv . . . . .
## PersPerFam . . . . .
## PctFam2Par . . . . .
## PctKids2Par . -0.04220914 -0.07832201 -0.11118010 -0.1411978
## PctYoungKids2Par . . . . .
## PctTeen2Par . . . . .
## PctWorkMomYoungKids . . . . .
## PctWorkMom . . . . .
## NumIlleg . . . . .
## PctIlleg . 0.03303125 0.06539192 0.09491414 0.1217523
## NumImmig . . . . .
## PctImmigRecent . . . . .
## PctImmigRec5 . . . . .
## PctImmigRec8 . . . . .
## PctImmigRec10 . . . . .
## PctRecentImmig . . . . .
## PctRecImmig5 . . . . .
## PctRecImmig8 . . . . .
## PctRecImmig10 . . . . .
## PctSpeakEnglOnly . . . . .
## PctNotSpeakEnglWell . . . . .
## PctLargHouseFam . . . . .
## PctLargHouseOccup . . . . .
## PersPerOccupHous . . . . .
## PersPerOwnOccHous . . . . .
## PersPerRentOccHous . . . . .
## PctPersOwnOccup . . . . .
## PctPersDenseHous . . . . .
## PctHousLess3BR . . . . .
## MedNumBR . . . . .
## HousVacant . . . . .
## PctHousOccup . . . . .
## PctHousOwnOcc . . . . .
## PctVacantBoarded . . . . .
## PctVacMore6Mos . . . . .
## MedYrHousBuilt . . . . .
## PctHousNoPhone . . . . .
## PctWOFullPlumb . . . . .
## OwnOccLowQuart . . . . .
## OwnOccMedVal . . . . .
## OwnOccHiQuart . . . . .
## RentLowQ . . . . .
## RentMedian . . . . .
## RentHighQ . . . . .
## MedRent . . . . .
## MedRentPctHousInc . . . . .
## MedOwnCostPctInc . . . . .
## MedOwnCostPctIncNoMtg . . . . .
## NumInShelters . . . . .
## NumStreet . . . . .
## PctForeignBorn . . . . .
## PctBornSameState . . . . .
## PctSameHouse85 . . . . .
## PctSameCity85 . . . . .
## PctSameState85 . . . . .
## LandArea . . . . .
## PopDens . . . . .
## PctUsePubTrans . . . . .
##
## (Intercept) 0.3068252092 0.33732688 0.3652837 0.39056495
## (Intercept) . . . .
## state . . . .
## fold . . . .
## population . . . .
## householdsize . . . .
## racepctblack . . . .
## racePctWhite -0.0007737576 -0.02244763 -0.0421901 -0.06015051
## racePctAsian . . . .
## racePctHisp . . . .
## agePct12t21 . . . .
## agePct12t29 . . . .
## agePct16t24 . . . .
## agePct65up . . . .
## numbUrban . . . .
## pctUrban . . . .
## medIncome . . . .
## pctWWage . . . .
## pctWFarmSelf . . . .
## pctWInvInc . . . .
## pctWSocSec . . . .
## pctWPubAsst . . . .
## pctWRetire . . . .
## medFamInc . . . .
## perCapInc . . . .
## whitePerCap . . . .
## blackPerCap . . . .
## indianPerCap . . . .
## AsianPerCap . . . .
## OtherPerCap . . . .
## HispPerCap . . . .
## NumUnderPov . . . .
## PctPopUnderPov . . . .
## PctLess9thGrade . . . .
## PctNotHSGrad . . . .
## PctBSorMore . . . .
## PctUnemployed . . . .
## PctEmploy . . . .
## PctEmplManu . . . .
## PctEmplProfServ . . . .
## PctOccupManu . . . .
## PctOccupMgmtProf . . . .
## MalePctDivorce . . . .
## MalePctNevMarr . . . .
## FemalePctDiv . . . .
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -0.1685953401 -0.19308543 -0.2156090 -0.23592973
## PctYoungKids2Par . . . .
## PctTeen2Par . . . .
## PctWorkMomYoungKids . . . .
## PctWorkMom . . . .
## NumIlleg . . . .
## PctIlleg 0.1455100960 0.14964707 0.1532583 0.15673045
## NumImmig . . . .
## PctImmigRecent . . . .
## PctImmigRec5 . . . .
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 . . . .
## PctRecImmig10 . . . .
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell . . . .
## PctLargHouseFam . . . .
## PctLargHouseOccup . . . .
## PersPerOccupHous . . . .
## PersPerOwnOccHous . . . .
## PersPerRentOccHous . . . .
## PctPersOwnOccup . . . .
## PctPersDenseHous . . . .
## PctHousLess3BR . . . .
## MedNumBR . . . .
## HousVacant . . . .
## PctHousOccup . . . .
## PctHousOwnOcc . . . .
## PctVacantBoarded . . . .
## PctVacMore6Mos . . . .
## MedYrHousBuilt . . . .
## PctHousNoPhone . . . .
## PctWOFullPlumb . . . .
## OwnOccLowQuart . . . .
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ . . . .
## RentMedian . . . .
## RentHighQ . . . .
## MedRent . . . .
## MedRentPctHousInc . . . .
## MedOwnCostPctInc . . . .
## MedOwnCostPctIncNoMtg . . . .
## NumInShelters . . . .
## NumStreet . . . .
## PctForeignBorn . . . .
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 . . . .
## PctSameState85 . . . .
## LandArea . . . .
## PopDens . . . .
## PctUsePubTrans . . . .
##
## (Intercept) 0.41380568 0.43477899 0.4538809 0.4714914 0.48417716
## (Intercept) . . . . .
## state . . . . .
## fold . . . . .
## population . . . . .
## householdsize . . . . .
## racepctblack . . . . .
## racePctWhite -0.07655236 -0.09146017 -0.1050436 -0.1174644 -0.12842509
## racePctAsian . . . . .
## racePctHisp . . . . .
## agePct12t21 . . . . .
## agePct12t29 . . . . .
## agePct16t24 . . . . .
## agePct65up . . . . .
## numbUrban . . . . .
## pctUrban . . . . .
## medIncome . . . . .
## pctWWage . . . . .
## pctWFarmSelf . . . . .
## pctWInvInc . . . . .
## pctWSocSec . . . . .
## pctWPubAsst . . . . .
## pctWRetire . . . . .
## medFamInc . . . . .
## perCapInc . . . . .
## whitePerCap . . . . .
## blackPerCap . . . . .
## indianPerCap . . . . .
## AsianPerCap . . . . .
## OtherPerCap . . . . .
## HispPerCap . . . . .
## NumUnderPov . . . . .
## PctPopUnderPov . . . . .
## PctLess9thGrade . . . . .
## PctNotHSGrad . . . . .
## PctBSorMore . . . . .
## PctUnemployed . . . . .
## PctEmploy . . . . .
## PctEmplManu . . . . .
## PctEmplProfServ . . . . .
## PctOccupManu . . . . .
## PctOccupMgmtProf . . . . .
## MalePctDivorce . . . . .
## MalePctNevMarr . . . . .
## FemalePctDiv . . . . .
## TotalPctDiv . . . . .
## PersPerFam . . . . .
## PctFam2Par . . . . .
## PctKids2Par -0.25465314 -0.27150846 -0.2868564 -0.3010406 -0.31059317
## PctYoungKids2Par . . . . .
## PctTeen2Par . . . . .
## PctWorkMomYoungKids . . . . .
## PctWorkMom . . . . .
## NumIlleg . . . . .
## PctIlleg 0.15970022 0.16259757 0.1652454 0.1674643 0.16917573
## NumImmig . . . . .
## PctImmigRecent . . . . .
## PctImmigRec5 . . . . .
## PctImmigRec8 . . . . .
## PctImmigRec10 . . . . .
## PctRecentImmig . . . . .
## PctRecImmig5 . . . . .
## PctRecImmig8 . . . . .
## PctRecImmig10 . . . . .
## PctSpeakEnglOnly . . . . .
## PctNotSpeakEnglWell . . . . .
## PctLargHouseFam . . . . .
## PctLargHouseOccup . . . . .
## PersPerOccupHous . . . . .
## PersPerOwnOccHous . . . . .
## PersPerRentOccHous . . . . .
## PctPersOwnOccup . . . . .
## PctPersDenseHous . . . . .
## PctHousLess3BR . . . . .
## MedNumBR . . . . .
## HousVacant . . . . 0.01401508
## PctHousOccup . . . . .
## PctHousOwnOcc . . . . .
## PctVacantBoarded . . . . .
## PctVacMore6Mos . . . . .
## MedYrHousBuilt . . . . .
## PctHousNoPhone . . . . .
## PctWOFullPlumb . . . . .
## OwnOccLowQuart . . . . .
## OwnOccMedVal . . . . .
## OwnOccHiQuart . . . . .
## RentLowQ . . . . .
## RentMedian . . . . .
## RentHighQ . . . . .
## MedRent . . . . .
## MedRentPctHousInc . . . . .
## MedOwnCostPctInc . . . . .
## MedOwnCostPctIncNoMtg . . . . .
## NumInShelters . . . . .
## NumStreet . . . . .
## PctForeignBorn . . . . .
## PctBornSameState . . . . .
## PctSameHouse85 . . . . .
## PctSameCity85 . . . . .
## PctSameState85 . . . . .
## LandArea . . . . .
## PopDens . . . . .
## PctUsePubTrans . . . . .
##
## (Intercept) 0.49739984 0.50875827 0.51891852 0.51804327
## (Intercept) . . . .
## state . . . .
## fold . . . .
## population . . . .
## householdsize . . . .
## racepctblack . . . .
## racePctWhite -0.13935519 -0.14887589 -0.15752139 -0.16521742
## racePctAsian . . . .
## racePctHisp . . . .
## agePct12t21 . . . .
## agePct12t29 . . . .
## agePct16t24 . . . .
## agePct65up . . . .
## numbUrban . . . .
## pctUrban . . . .
## medIncome . . . .
## pctWWage . . . .
## pctWFarmSelf . . . .
## pctWInvInc . . . .
## pctWSocSec . . . .
## pctWPubAsst . . . .
## pctWRetire . . . .
## medFamInc . . . .
## perCapInc . . . .
## whitePerCap . . . .
## blackPerCap . . . .
## indianPerCap . . . .
## AsianPerCap . . . .
## OtherPerCap . . . .
## HispPerCap . . . .
## NumUnderPov . . . .
## PctPopUnderPov . . . .
## PctLess9thGrade . . . .
## PctNotHSGrad . . . .
## PctBSorMore . . . .
## PctUnemployed . . . .
## PctEmploy . . . .
## PctEmplManu . . . .
## PctEmplProfServ . . . .
## PctOccupManu . . . .
## PctOccupMgmtProf . . . .
## MalePctDivorce . . . .
## MalePctNevMarr . . . .
## FemalePctDiv . . . .
## TotalPctDiv . . . 0.00812099
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -0.32042909 -0.32906677 -0.33674023 -0.33539208
## PctYoungKids2Par . . . .
## PctTeen2Par . . . .
## PctWorkMomYoungKids . . . .
## PctWorkMom . . . .
## NumIlleg . . . .
## PctIlleg 0.16693519 0.16552037 0.16440674 0.16694965
## NumImmig . . . .
## PctImmigRecent . . . .
## PctImmigRec5 . . . .
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 . . . .
## PctRecImmig10 . . . .
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell . . . .
## PctLargHouseFam . . . .
## PctLargHouseOccup . . . .
## PersPerOccupHous . . . .
## PersPerOwnOccHous . . . .
## PersPerRentOccHous . . . .
## PctPersOwnOccup . . . .
## PctPersDenseHous . . . .
## PctHousLess3BR . . . .
## MedNumBR . . . .
## HousVacant 0.03589051 0.05583704 0.07402335 0.08950784
## PctHousOccup . . . .
## PctHousOwnOcc . . . .
## PctVacantBoarded . . . .
## PctVacMore6Mos . . . .
## MedYrHousBuilt . . . .
## PctHousNoPhone . . . .
## PctWOFullPlumb . . . .
## OwnOccLowQuart . . . .
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ . . . .
## RentMedian . . . .
## RentHighQ . . . .
## MedRent . . . .
## MedRentPctHousInc . . . .
## MedOwnCostPctInc . . . .
## MedOwnCostPctIncNoMtg . . . .
## NumInShelters . . . .
## NumStreet . . . .
## PctForeignBorn . . . .
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 . . . .
## PctSameState85 . . . .
## LandArea . . . .
## PopDens . . . .
## PctUsePubTrans . . . .
##
## (Intercept) 0.510239819 0.501044507 0.49099645 0.48204741
## (Intercept) . . . .
## state . . . .
## fold . . . .
## population . . . .
## householdsize . . . .
## racepctblack . . . .
## racePctWhite -0.171592314 -0.172038063 -0.17308383 -0.17447569
## racePctAsian . . . .
## racePctHisp . . . .
## agePct12t21 . . . .
## agePct12t29 . . . .
## agePct16t24 . . . .
## agePct65up . . . .
## numbUrban . . . .
## pctUrban . . . .
## medIncome . . . .
## pctWWage . . . .
## pctWFarmSelf . . . .
## pctWInvInc . . . .
## pctWSocSec . . . .
## pctWPubAsst . . . .
## pctWRetire . . . .
## medFamInc . . . .
## perCapInc . . . .
## whitePerCap . . . .
## blackPerCap . . . .
## indianPerCap . . . .
## AsianPerCap . . . .
## OtherPerCap . . . .
## HispPerCap . . . .
## NumUnderPov . . . .
## PctPopUnderPov . . . .
## PctLess9thGrade . . . .
## PctNotHSGrad . . . .
## PctBSorMore . . . .
## PctUnemployed . . . .
## PctEmploy . . . .
## PctEmplManu . . . .
## PctEmplProfServ . . . .
## PctOccupManu . . . .
## PctOccupMgmtProf . . . .
## MalePctDivorce . 0.008170492 0.02350898 0.04257078
## MalePctNevMarr . . . .
## FemalePctDiv . . . .
## TotalPctDiv 0.020577876 0.021528748 0.01599127 0.00613436
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -0.328691333 -0.325878436 -0.32097957 -0.31622984
## PctYoungKids2Par . . . .
## PctTeen2Par . . . .
## PctWorkMomYoungKids . . . .
## PctWorkMom . . . .
## NumIlleg . . . .
## PctIlleg 0.171227041 0.175334590 0.17988992 0.18391337
## NumImmig . . . .
## PctImmigRecent . . . .
## PctImmigRec5 . . . .
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 . . . .
## PctRecImmig10 . . . .
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell . . . .
## PctLargHouseFam . . . .
## PctLargHouseOccup . . . .
## PersPerOccupHous . . . .
## PersPerOwnOccHous . . . .
## PersPerRentOccHous . . . .
## PctPersOwnOccup . . . .
## PctPersDenseHous 0.001410899 0.010304964 0.01863110 0.02632764
## PctHousLess3BR . . . .
## MedNumBR . . . .
## HousVacant 0.098594259 0.105988600 0.11253576 0.11838301
## PctHousOccup . . . .
## PctHousOwnOcc . . . .
## PctVacantBoarded . . . .
## PctVacMore6Mos . . . .
## MedYrHousBuilt . . . .
## PctHousNoPhone . . . .
## PctWOFullPlumb . . . .
## OwnOccLowQuart . . . .
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ . . . .
## RentMedian . . . .
## RentHighQ . . . .
## MedRent . . . .
## MedRentPctHousInc . . . .
## MedOwnCostPctInc . . . .
## MedOwnCostPctIncNoMtg . . . .
## NumInShelters . . . .
## NumStreet 0.011512470 0.024478737 0.03613088 0.04672960
## PctForeignBorn . . . .
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 . . . .
## PctSameState85 . . . .
## LandArea . . . .
## PopDens . . . .
## PctUsePubTrans . . . .
##
## (Intercept) 4.754156e-01 0.4696311002 0.4629715678 0.4589318859
## (Intercept) . . . .
## state -6.536632e-05 -0.0001525771 -0.0002430974 -0.0003211076
## fold . . . .
## population . . . .
## householdsize . . . .
## racepctblack . . . .
## racePctWhite -1.749973e-01 -0.1740921963 -0.1734769667 -0.1734975054
## racePctAsian . . . .
## racePctHisp . . . .
## agePct12t21 . . . .
## agePct12t29 . . . .
## agePct16t24 . . . .
## agePct65up . . . .
## numbUrban . . . .
## pctUrban . . . 0.0014936499
## medIncome . . . .
## pctWWage . . . .
## pctWFarmSelf . . . .
## pctWInvInc . . . .
## pctWSocSec . . . .
## pctWPubAsst . . . .
## pctWRetire . . . .
## medFamInc . . . .
## perCapInc . . . .
## whitePerCap . . . .
## blackPerCap . . . .
## indianPerCap . . . .
## AsianPerCap . . . .
## OtherPerCap . . . .
## HispPerCap . . . .
## NumUnderPov . . . .
## PctPopUnderPov . . . .
## PctLess9thGrade . . . .
## PctNotHSGrad . . . .
## PctBSorMore . . . .
## PctUnemployed . . . .
## PctEmploy . . . .
## PctEmplManu . . . .
## PctEmplProfServ . . . .
## PctOccupManu . . . .
## PctOccupMgmtProf . . . .
## MalePctDivorce 5.716011e-02 0.0637998700 0.0704139980 0.0773060273
## MalePctNevMarr . . . .
## FemalePctDiv . . . .
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -3.121808e-01 -0.3091819160 -0.3046471316 -0.3016743792
## PctYoungKids2Par . . . .
## PctTeen2Par . . . .
## PctWorkMomYoungKids . . . .
## PctWorkMom . . . -0.0033347329
## NumIlleg . . . .
## PctIlleg 1.878857e-01 0.1919477666 0.1943782947 0.1957624355
## NumImmig . . . .
## PctImmigRecent . . . .
## PctImmigRec5 . . . .
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 . . . .
## PctRecImmig10 . . . .
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell . . . .
## PctLargHouseFam . . . .
## PctLargHouseOccup . . . .
## PersPerOccupHous . . . .
## PersPerOwnOccHous . . . .
## PersPerRentOccHous . . . .
## PctPersOwnOccup . . . .
## PctPersDenseHous 3.215887e-02 0.0371031389 0.0412731769 0.0436930378
## PctHousLess3BR . . . .
## MedNumBR . . . .
## HousVacant 1.236602e-01 0.1286673812 0.1316366764 0.1331850227
## PctHousOccup . . . .
## PctHousOwnOcc . . . .
## PctVacantBoarded . 0.0008907537 0.0064892650 0.0109728973
## PctVacMore6Mos . . . .
## MedYrHousBuilt . . . .
## PctHousNoPhone . . . .
## PctWOFullPlumb . . . .
## OwnOccLowQuart . . . .
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ . . . .
## RentMedian . . . .
## RentHighQ . . . .
## MedRent . . . .
## MedRentPctHousInc . . . .
## MedOwnCostPctInc . . . .
## MedOwnCostPctIncNoMtg . . . .
## NumInShelters . . . .
## NumStreet 5.573299e-02 0.0634915917 0.0709332465 0.0776267539
## PctForeignBorn . . . .
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 . . . .
## PctSameState85 . . . .
## LandArea . . . .
## PopDens . . . .
## PctUsePubTrans . . . .
##
## (Intercept) 0.4596702494 0.4615500800 0.4509845545 0.4377146475
## (Intercept) . . . .
## state -0.0003878423 -0.0004488919 -0.0005081911 -0.0005654171
## fold . . . .
## population . . . .
## householdsize . . . .
## racepctblack . . 0.0100682689 0.0243910208
## racePctWhite -0.1728148879 -0.1724886286 -0.1635782672 -0.1507048697
## racePctAsian . . . .
## racePctHisp . . . .
## agePct12t21 . . . .
## agePct12t29 . . . .
## agePct16t24 . . . .
## agePct65up . . . .
## numbUrban . . . .
## pctUrban 0.0045620679 0.0076901986 0.0104401482 0.0129913262
## medIncome . . . .
## pctWWage . . . .
## pctWFarmSelf . . . .
## pctWInvInc . . . .
## pctWSocSec . . . .
## pctWPubAsst . . . .
## pctWRetire . . . .
## medFamInc . . . .
## perCapInc . . . .
## whitePerCap . . . .
## blackPerCap . . . .
## indianPerCap . . . .
## AsianPerCap . . . .
## OtherPerCap . . . .
## HispPerCap . . . .
## NumUnderPov . . . .
## PctPopUnderPov . . . .
## PctLess9thGrade . . . .
## PctNotHSGrad . . . .
## PctBSorMore . . . .
## PctUnemployed . . . .
## PctEmploy . . . .
## PctEmplManu . . . .
## PctEmplProfServ . . . .
## PctOccupManu . . . .
## PctOccupMgmtProf . . . .
## MalePctDivorce 0.0827139379 0.0874402147 0.0933416620 0.0980631911
## MalePctNevMarr . . . .
## FemalePctDiv . . . .
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -0.3016120668 -0.2989499300 -0.2923723366 -0.2876813375
## PctYoungKids2Par . . . .
## PctTeen2Par . . . .
## PctWorkMomYoungKids . . . .
## PctWorkMom -0.0099168915 -0.0154880506 -0.0214561748 -0.0271822017
## NumIlleg . . . .
## PctIlleg 0.1966425629 0.1988003896 0.1995621203 0.1976636987
## NumImmig . . . .
## PctImmigRecent . . . .
## PctImmigRec5 . . . .
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 . . . .
## PctRecImmig10 . . . .
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell . . . .
## PctLargHouseFam . . . .
## PctLargHouseOccup . . . .
## PersPerOccupHous . . . .
## PersPerOwnOccHous . . . .
## PersPerRentOccHous . . . .
## PctPersOwnOccup . . . .
## PctPersDenseHous 0.0448119610 0.0457185911 0.0526862497 0.0623139156
## PctHousLess3BR . . . .
## MedNumBR . . . .
## HousVacant 0.1322513665 0.1286187625 0.1257597866 0.1236764509
## PctHousOccup -0.0023697847 -0.0088766577 -0.0141032365 -0.0181840229
## PctHousOwnOcc . . . .
## PctVacantBoarded 0.0141398790 0.0171280860 0.0195200084 0.0215327611
## PctVacMore6Mos . . . .
## MedYrHousBuilt . . . .
## PctHousNoPhone . . . .
## PctWOFullPlumb . . . .
## OwnOccLowQuart . . . .
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ . . . .
## RentMedian . . . .
## RentHighQ . . . .
## MedRent . . . .
## MedRentPctHousInc . . . .
## MedOwnCostPctInc . . . .
## MedOwnCostPctIncNoMtg . . . .
## NumInShelters . . . .
## NumStreet 0.0846207118 0.0930040727 0.1004293654 0.1071000227
## PctForeignBorn . . . .
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 . . . .
## PctSameState85 . . . .
## LandArea . . . .
## PopDens . . . .
## PctUsePubTrans . . . .
##
## (Intercept) 0.4260047083 0.4153567185 0.4056720268 0.397865561
## (Intercept) . . . .
## state -0.0006174526 -0.0006648481 -0.0007080246 -0.000745687
## fold . . . .
## population . . . .
## householdsize . . . .
## racepctblack 0.0372240076 0.0488883559 0.0595024744 0.069689214
## racePctWhite -0.1391248139 -0.1285957327 -0.1190138700 -0.109966304
## racePctAsian . . . .
## racePctHisp . . . .
## agePct12t21 . . . .
## agePct12t29 . . . -0.002499253
## agePct16t24 . . . .
## agePct65up . . . .
## numbUrban . . . .
## pctUrban 0.0153233652 0.0174481920 0.0193844230 0.021080151
## medIncome . . . .
## pctWWage . . . .
## pctWFarmSelf . . . .
## pctWInvInc . . . .
## pctWSocSec . . . .
## pctWPubAsst . . . .
## pctWRetire . . . .
## medFamInc . . . .
## perCapInc . . . .
## whitePerCap . . . .
## blackPerCap . . . .
## indianPerCap . . . .
## AsianPerCap . . . .
## OtherPerCap . . . .
## HispPerCap . . . .
## NumUnderPov . . . .
## PctPopUnderPov . . . .
## PctLess9thGrade . . . .
## PctNotHSGrad . . . .
## PctBSorMore . . . .
## PctUnemployed . . . .
## PctEmploy . . . .
## PctEmplManu . . . .
## PctEmplProfServ . . . .
## PctOccupManu . . . .
## PctOccupMgmtProf . . . .
## MalePctDivorce 0.1022432644 0.1060514579 0.1095186392 0.112244451
## MalePctNevMarr . . . .
## FemalePctDiv . . . .
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -0.2836593609 -0.2799931445 -0.2766585104 -0.274115884
## PctYoungKids2Par . . . .
## PctTeen2Par . . . .
## PctWorkMomYoungKids . . . .
## PctWorkMom -0.0323895647 -0.0371327285 -0.0414539205 -0.045144908
## NumIlleg . . . .
## PctIlleg 0.1959132166 0.1943333226 0.1928965320 0.191475055
## NumImmig . . . .
## PctImmigRecent . . . .
## PctImmigRec5 . . . .
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 . . . .
## PctRecImmig10 . . . .
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell . . . .
## PctLargHouseFam . . . .
## PctLargHouseOccup . . . .
## PersPerOccupHous . . . .
## PersPerOwnOccHous . . . .
## PersPerRentOccHous . . . .
## PctPersOwnOccup . . . .
## PctPersDenseHous 0.0709582060 0.0788177875 0.0859702885 0.093214680
## PctHousLess3BR . . . .
## MedNumBR . . . .
## HousVacant 0.1217933171 0.1200759965 0.1185108569 0.117151592
## PctHousOccup -0.0219023482 -0.0252937025 -0.0283847386 -0.030955822
## PctHousOwnOcc . . . .
## PctVacantBoarded 0.0233578630 0.0250213025 0.0265368992 0.027783033
## PctVacMore6Mos . . . .
## MedYrHousBuilt . . . .
## PctHousNoPhone . . . .
## PctWOFullPlumb . . . .
## OwnOccLowQuart . . . .
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ . . . .
## RentMedian . . . .
## RentHighQ . . . .
## MedRent . . . .
## MedRentPctHousInc . . . .
## MedOwnCostPctInc . . . .
## MedOwnCostPctIncNoMtg . . . .
## NumInShelters . . . .
## NumStreet 0.1131701930 0.1187007765 0.1237400166 0.128369221
## PctForeignBorn . . . .
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 . . . .
## PctSameState85 . . . .
## LandArea . . . .
## PopDens . . . .
## PctUsePubTrans . . . .
##
## (Intercept) 0.3937603438 0.3892448120 0.3848451767 3.841359e-01
## (Intercept) . . . .
## state -0.0007742923 -0.0008015744 -0.0008253778 -8.440405e-04
## fold . . . -3.840982e-05
## population . . . .
## householdsize . . . .
## racepctblack 0.0770643529 0.0844682310 0.0914823357 9.710429e-02
## racePctWhite -0.1020630565 -0.0947515234 -0.0878749075 -8.158592e-02
## racePctAsian . . . .
## racePctHisp . . . .
## agePct12t21 . . . .
## agePct12t29 -0.0084890794 -0.0136092764 -0.0181039082 -2.303420e-02
## agePct16t24 . . . .
## agePct65up . . . .
## numbUrban . . . .
## pctUrban 0.0225225293 0.0238374200 0.0249836454 2.612015e-02
## medIncome . . . .
## pctWWage . . . .
## pctWFarmSelf . . . .
## pctWInvInc . . -0.0002946125 -4.032793e-03
## pctWSocSec . . . .
## pctWPubAsst . . . .
## pctWRetire . . . .
## medFamInc . . . .
## perCapInc . . . .
## whitePerCap . . . .
## blackPerCap . . . .
## indianPerCap . . . .
## AsianPerCap . . . .
## OtherPerCap . . 0.0011755934 4.692997e-03
## HispPerCap . . . .
## NumUnderPov . . . .
## PctPopUnderPov . . . .
## PctLess9thGrade . . . .
## PctNotHSGrad . . . .
## PctBSorMore . . . .
## PctUnemployed . . . .
## PctEmploy . . . .
## PctEmplManu . . . .
## PctEmplProfServ . . . .
## PctOccupManu . . . .
## PctOccupMgmtProf . . . .
## MalePctDivorce 0.1131256359 0.1144353002 0.1155997938 1.150819e-01
## MalePctNevMarr . . . .
## FemalePctDiv . . . .
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -0.2732641460 -0.2718880319 -0.2708850424 -2.708422e-01
## PctYoungKids2Par . . . .
## PctTeen2Par . . . .
## PctWorkMomYoungKids . . . .
## PctWorkMom -0.0476426088 -0.0501101045 -0.0523668615 -5.425769e-02
## NumIlleg . . . .
## PctIlleg 0.1918216728 0.1917729011 0.1914147003 1.911730e-01
## NumImmig . . . .
## PctImmigRecent . . . .
## PctImmigRec5 . . . .
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 . . . .
## PctRecImmig10 . . . .
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell . . . .
## PctLargHouseFam . . . .
## PctLargHouseOccup . . . .
## PersPerOccupHous . . . .
## PersPerOwnOccHous . . . .
## PersPerRentOccHous . . . .
## PctPersOwnOccup . . . .
## PctPersDenseHous 0.1000936845 0.1064542015 0.1123847746 1.165768e-01
## PctHousLess3BR . . . .
## MedNumBR . . . .
## HousVacant 0.1165239229 0.1157394167 0.1150078095 1.146044e-01
## PctHousOccup -0.0332153453 -0.0352552556 -0.0370761812 -3.864714e-02
## PctHousOwnOcc . . . .
## PctVacantBoarded 0.0287459640 0.0296479928 0.0305039711 3.115474e-02
## PctVacMore6Mos . . . .
## MedYrHousBuilt . . . .
## PctHousNoPhone . . . .
## PctWOFullPlumb . . . .
## OwnOccLowQuart . . . .
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ . . . .
## RentMedian . . . .
## RentHighQ . . . .
## MedRent . . . .
## MedRentPctHousInc . . . .
## MedOwnCostPctInc . . . .
## MedOwnCostPctIncNoMtg . . . -8.940019e-04
## NumInShelters . . . .
## NumStreet 0.1322147602 0.1358571366 0.1392740611 1.427040e-01
## PctForeignBorn . . . .
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 . . . .
## PctSameState85 . . . .
## LandArea . . . .
## PopDens . . . .
## PctUsePubTrans . . . .
##
## (Intercept) 0.3874494468 0.3894502297 0.3915517926 0.3912942615
## (Intercept) . . . .
## state -0.0008543246 -0.0008643687 -0.0008734465 -0.0008785740
## fold -0.0002115999 -0.0003703024 -0.0005147981 -0.0006425091
## population . . . .
## householdsize . . . .
## racepctblack 0.1016018155 0.1062287303 0.1103236232 0.1158416045
## racePctWhite -0.0759341724 -0.0704369548 -0.0656022489 -0.0591770834
## racePctAsian . . . .
## racePctHisp . . . .
## agePct12t21 . . . .
## agePct12t29 -0.0285540516 -0.0334457770 -0.0378933315 -0.0419061639
## agePct16t24 . . . .
## agePct65up . . . .
## numbUrban . . . .
## pctUrban 0.0272413372 0.0282451908 0.0291642517 0.0298824294
## medIncome . . . .
## pctWWage . . . .
## pctWFarmSelf . . . .
## pctWInvInc -0.0082142253 -0.0120099077 -0.0154882015 -0.0194983984
## pctWSocSec . . . .
## pctWPubAsst . . . .
## pctWRetire . . . .
## medFamInc . . . .
## perCapInc . . . .
## whitePerCap . . . .
## blackPerCap . . . .
## indianPerCap . . . -0.0022254808
## AsianPerCap . . . 0.0011894979
## OtherPerCap 0.0082376009 0.0114041913 0.0142926970 0.0169153701
## HispPerCap . . . .
## NumUnderPov . . . .
## PctPopUnderPov . . . .
## PctLess9thGrade . . . .
## PctNotHSGrad . . . .
## PctBSorMore . . . .
## PctUnemployed . . . .
## PctEmploy . . . .
## PctEmplManu . . . .
## PctEmplProfServ . . . .
## PctOccupManu . . . .
## PctOccupMgmtProf . . . .
## MalePctDivorce 0.1129855981 0.1114689756 0.1100549129 0.1090247633
## MalePctNevMarr . . . .
## FemalePctDiv . . . .
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -0.2709287623 -0.2703956945 -0.2700243619 -0.2691360260
## PctYoungKids2Par . . . .
## PctTeen2Par . . . .
## PctWorkMomYoungKids . . . .
## PctWorkMom -0.0559067123 -0.0574481739 -0.0588531351 -0.0598529531
## NumIlleg . . . .
## PctIlleg 0.1928108358 0.1942194575 0.1954208876 0.1963246484
## NumImmig . . . .
## PctImmigRecent . . . .
## PctImmigRec5 . . . .
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 . . . .
## PctRecImmig10 . . . 0.0012739858
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell . . . .
## PctLargHouseFam . . . .
## PctLargHouseOccup . . . .
## PersPerOccupHous . . . .
## PersPerOwnOccHous . . . .
## PersPerRentOccHous . . . .
## PctPersOwnOccup . . . .
## PctPersDenseHous 0.1192969037 0.1220825372 0.1245044591 0.1260802010
## PctHousLess3BR . . . .
## MedNumBR . . . .
## HousVacant 0.1138425611 0.1131553555 0.1125145802 0.1119010410
## PctHousOccup -0.0408503813 -0.0428188513 -0.0446118164 -0.0463137273
## PctHousOwnOcc . . . .
## PctVacantBoarded 0.0319812727 0.0327686480 0.0334834422 0.0344721575
## PctVacMore6Mos . . . .
## MedYrHousBuilt . . . .
## PctHousNoPhone . . . .
## PctWOFullPlumb . . . .
## OwnOccLowQuart . . . .
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ . . . .
## RentMedian . . . .
## RentHighQ . . . .
## MedRent . . . .
## MedRentPctHousInc . . . .
## MedOwnCostPctInc . . . .
## MedOwnCostPctIncNoMtg -0.0052234489 -0.0090983184 -0.0126243445 -0.0162299953
## NumInShelters . . . 0.0003900858
## NumStreet 0.1458114403 0.1486371228 0.1512304736 0.1529975910
## PctForeignBorn . . . 0.0010980459
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 . . . .
## PctSameState85 . . . .
## LandArea . . . .
## PopDens . . . .
## PctUsePubTrans . . . .
##
## (Intercept) 0.3961400927 0.3986661505 0.3997238013 0.4004378862
## (Intercept) . . . .
## state -0.0008831837 -0.0008834142 -0.0008797144 -0.0008769908
## fold -0.0007549116 -0.0008552611 -0.0009425527 -0.0010209732
## population . . . .
## householdsize . . . .
## racepctblack 0.1214760734 0.1270882870 0.1326276477 0.1380748712
## racePctWhite -0.0525656771 -0.0465907663 -0.0415375938 -0.0369191895
## racePctAsian . . . .
## racePctHisp . . . .
## agePct12t21 . . . .
## agePct12t29 -0.0473329008 -0.0533873335 -0.0575247483 -0.0596406759
## agePct16t24 . . . .
## agePct65up . . . .
## numbUrban . . . .
## pctUrban 0.0306706465 0.0314612324 0.0320172198 0.0325829902
## medIncome . . . .
## pctWWage . . -0.0009075784 -0.0042867784
## pctWFarmSelf . . . .
## pctWInvInc -0.0240152586 -0.0285226836 -0.0333761850 -0.0384849609
## pctWSocSec . . . .
## pctWPubAsst . . . .
## pctWRetire -0.0037054470 -0.0076308972 -0.0116021257 -0.0156932335
## medFamInc . . . .
## perCapInc . . . .
## whitePerCap . . . .
## blackPerCap . . . -0.0009288090
## indianPerCap -0.0050910483 -0.0076571260 -0.0099148879 -0.0118245790
## AsianPerCap 0.0028807884 0.0045372119 0.0060594877 0.0075422457
## OtherPerCap 0.0190772332 0.0211033895 0.0229914150 0.0248894775
## HispPerCap . . . .
## NumUnderPov . . . .
## PctPopUnderPov . . . .
## PctLess9thGrade . . . .
## PctNotHSGrad . . . .
## PctBSorMore . . . .
## PctUnemployed . . . .
## PctEmploy . . . .
## PctEmplManu . -0.0004257463 -0.0023235791 -0.0041307573
## PctEmplProfServ . . . .
## PctOccupManu . . . .
## PctOccupMgmtProf . . . .
## MalePctDivorce 0.1067935143 0.1042923230 0.1027130999 0.1022434849
## MalePctNevMarr . . . .
## FemalePctDiv . . . .
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -0.2705885772 -0.2693398403 -0.2651591427 -0.2576406787
## PctYoungKids2Par -0.0003638407 -0.0018550505 -0.0040535630 -0.0062982279
## PctTeen2Par . . . .
## PctWorkMomYoungKids . . . .
## PctWorkMom -0.0608695050 -0.0616552913 -0.0622325572 -0.0625119787
## NumIlleg . . . .
## PctIlleg 0.1954306012 0.1946448047 0.1940302002 0.1944308275
## NumImmig . . . .
## PctImmigRecent . . . .
## PctImmigRec5 . . . .
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 . . . .
## PctRecImmig10 0.0024871944 0.0029418106 0.0038031929 0.0050852521
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell . . . .
## PctLargHouseFam . . . .
## PctLargHouseOccup . . . .
## PersPerOccupHous . . . .
## PersPerOwnOccHous . . . .
## PersPerRentOccHous . . . .
## PctPersOwnOccup . . . .
## PctPersDenseHous 0.1256312907 0.1252266505 0.1238240721 0.1219164533
## PctHousLess3BR 0.0009737098 0.0035537827 0.0058114689 0.0065789313
## MedNumBR . . . .
## HousVacant 0.1097346944 0.1079442220 0.1060347401 0.1036983626
## PctHousOccup -0.0480532652 -0.0490708951 -0.0502720183 -0.0519829093
## PctHousOwnOcc . . . .
## PctVacantBoarded 0.0356030168 0.0367091172 0.0376719594 0.0389765518
## PctVacMore6Mos . . -0.0014574757 -0.0045302148
## MedYrHousBuilt . . . .
## PctHousNoPhone . . . .
## PctWOFullPlumb . . . .
## OwnOccLowQuart . . . .
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ . . . .
## RentMedian . . . .
## RentHighQ . . . .
## MedRent . . . .
## MedRentPctHousInc . 0.0020686785 0.0044570077 0.0063463058
## MedOwnCostPctInc . . . .
## MedOwnCostPctIncNoMtg -0.0201643834 -0.0241510188 -0.0279232743 -0.0310797529
## NumInShelters 0.0041389476 0.0073142823 0.0104626599 0.0138008176
## NumStreet 0.1532153761 0.1534333142 0.1536021534 0.1537816017
## PctForeignBorn 0.0031785920 0.0049217767 0.0064521863 0.0081028603
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 . 0.0001835284 0.0027001209 0.0055110882
## PctSameState85 . . . .
## LandArea . . . .
## PopDens . . . .
## PctUsePubTrans . . . .
##
## (Intercept) 0.4047532227 0.407172533 0.4075711950 0.4218281767
## (Intercept) . . . .
## state -0.0008757008 -0.000874072 -0.0008741952 -0.0008662521
## fold -0.0010950481 -0.001157936 -0.0012117857 -0.0012822283
## population . . . .
## householdsize . . . .
## racepctblack 0.1408005831 0.143914385 0.1476381735 0.1508715707
## racePctWhite -0.0351522997 -0.032595554 -0.0291477738 -0.0291762171
## racePctAsian . . . .
## racePctHisp . . . .
## agePct12t21 . . . .
## agePct12t29 -0.0624459147 -0.065052446 -0.0673737060 -0.0625795593
## agePct16t24 . . . .
## agePct65up . . . .
## numbUrban . . . .
## pctUrban 0.0330748274 0.033509722 0.0339033850 0.0340245317
## medIncome . . . .
## pctWWage -0.0060493725 -0.007818111 -0.0089487074 -0.0136695905
## pctWFarmSelf . . . 0.0016874962
## pctWInvInc -0.0415765187 -0.045438522 -0.0485619704 -0.0492392161
## pctWSocSec . . . .
## pctWPubAsst . . . .
## pctWRetire -0.0195227630 -0.022835245 -0.0256436734 -0.0315264013
## medFamInc . . . .
## perCapInc . . . .
## whitePerCap . . . .
## blackPerCap -0.0034176453 -0.005559969 -0.0072136876 -0.0080872559
## indianPerCap -0.0135197792 -0.015030804 -0.0162930516 -0.0173944371
## AsianPerCap 0.0089093100 0.010200162 0.0115220077 0.0132242455
## OtherPerCap 0.0267289406 0.028378700 0.0300176057 0.0318417655
## HispPerCap . . . .
## NumUnderPov . . . .
## PctPopUnderPov . . -0.0010177734 -0.0189730354
## PctLess9thGrade . . . .
## PctNotHSGrad . . . .
## PctBSorMore . . . .
## PctUnemployed . . . .
## PctEmploy . . . .
## PctEmplManu -0.0056198933 -0.006890380 -0.0077965049 -0.0090066428
## PctEmplProfServ . . . .
## PctOccupManu . . . .
## PctOccupMgmtProf . . . .
## MalePctDivorce 0.1012995184 0.100311452 0.0995635751 0.0984749610
## MalePctNevMarr . . . .
## FemalePctDiv . . . .
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -0.2539315510 -0.249449097 -0.2449651756 -0.2450223677
## PctYoungKids2Par -0.0075134642 -0.008734988 -0.0096822995 -0.0134127099
## PctTeen2Par . . . .
## PctWorkMomYoungKids . . . .
## PctWorkMom -0.0631500571 -0.063611760 -0.0641036291 -0.0681172391
## NumIlleg . . . .
## PctIlleg 0.1942835431 0.194575498 0.1949710864 0.1929241562
## NumImmig . -0.007491509 -0.0232866758 -0.0352863124
## PctImmigRecent . . . .
## PctImmigRec5 . . . .
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 . . . .
## PctRecImmig10 0.0057853420 0.007424518 0.0098063491 0.0105094134
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell . . . .
## PctLargHouseFam . . . .
## PctLargHouseOccup . . . .
## PersPerOccupHous . . . .
## PersPerOwnOccHous . . . .
## PersPerRentOccHous . . . .
## PctPersOwnOccup . . . .
## PctPersDenseHous 0.1194291803 0.117420130 0.1166056010 0.1170447274
## PctHousLess3BR 0.0075331266 0.008337614 0.0089353102 0.0096027207
## MedNumBR . . . .
## HousVacant 0.1019038807 0.101339794 0.1013805555 0.1008920107
## PctHousOccup -0.0534918456 -0.054602115 -0.0556779915 -0.0574440347
## PctHousOwnOcc . . . .
## PctVacantBoarded 0.0400986011 0.040891373 0.0413569854 0.0424092439
## PctVacMore6Mos -0.0072996173 -0.009773134 -0.0120794013 -0.0145090647
## MedYrHousBuilt . . . .
## PctHousNoPhone . . . .
## PctWOFullPlumb . . . .
## OwnOccLowQuart . . . .
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ . . -0.0023248054 -0.0120966305
## RentMedian . . . .
## RentHighQ . . . .
## MedRent . . . .
## MedRentPctHousInc 0.0080292614 0.009663808 0.0119148032 0.0184923439
## MedOwnCostPctInc . . . .
## MedOwnCostPctIncNoMtg -0.0336326439 -0.036194477 -0.0385886401 -0.0410493846
## NumInShelters 0.0159114774 0.020080124 0.0270833456 0.0323097197
## NumStreet 0.1543273085 0.156209029 0.1597286294 0.1624803521
## PctForeignBorn 0.0092766812 0.010707098 0.0130978842 0.0160631878
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 0.0080203763 0.010388411 0.0125155250 0.0147902042
## PctSameState85 . . . .
## LandArea . . . .
## PopDens . . . .
## PctUsePubTrans . . . .
##
## (Intercept) 0.4351122191 0.4507371230 0.4632772175 0.4741976445
## (Intercept) . . . .
## state -0.0008581465 -0.0008431946 -0.0008238874 -0.0008132286
## fold -0.0013467993 -0.0014023960 -0.0014455411 -0.0014808959
## population . . . .
## householdsize . . . .
## racepctblack 0.1535818419 0.1574108728 0.1616398235 0.1661511465
## racePctWhite -0.0283557572 -0.0261968304 -0.0240692730 -0.0238839022
## racePctAsian . . . .
## racePctHisp . . . .
## agePct12t21 . . . .
## agePct12t29 -0.0584637686 -0.0592190999 -0.0659472046 -0.0744572376
## agePct16t24 . . . .
## agePct65up . . . .
## numbUrban . . . .
## pctUrban 0.0342229992 0.0344193488 0.0346205294 0.0348671229
## medIncome . . . .
## pctWWage -0.0180085548 -0.0235810714 -0.0274363063 -0.0349029983
## pctWFarmSelf 0.0040071403 0.0063605923 0.0082580724 0.0102051818
## pctWInvInc -0.0502278037 -0.0553541465 -0.0642423210 -0.0677263332
## pctWSocSec . 0.0001278185 0.0006873146 0.0027873172
## pctWPubAsst . . . .
## pctWRetire -0.0366446454 -0.0422559467 -0.0456305609 -0.0489152606
## medFamInc . . . .
## perCapInc . . . .
## whitePerCap . . . -0.0095647913
## blackPerCap -0.0089361826 -0.0105542357 -0.0123855792 -0.0137121310
## indianPerCap -0.0184767235 -0.0197259952 -0.0210134980 -0.0218588737
## AsianPerCap 0.0147215589 0.0154785944 0.0160369013 0.0174281950
## OtherPerCap 0.0334832173 0.0343911859 0.0355494274 0.0365174087
## HispPerCap 0.0002758946 0.0020850317 0.0029810062 0.0047165394
## NumUnderPov . . . .
## PctPopUnderPov -0.0350772930 -0.0505939359 -0.0612280679 -0.0674291370
## PctLess9thGrade . . . .
## PctNotHSGrad . . . .
## PctBSorMore . . . .
## PctUnemployed . . -0.0037313021 -0.0074964285
## PctEmploy . . 0.0002578542 0.0100466156
## PctEmplManu -0.0100011820 -0.0107625116 -0.0113468581 -0.0124329030
## PctEmplProfServ . . . .
## PctOccupManu . . . .
## PctOccupMgmtProf . . . .
## MalePctDivorce 0.0969425547 0.0955556177 0.0953757200 0.0952752071
## MalePctNevMarr . 0.0054149839 0.0149881802 0.0249238755
## FemalePctDiv . . . .
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -0.2476118997 -0.2484510437 -0.2435136299 -0.2364904597
## PctYoungKids2Par -0.0161995194 -0.0193910550 -0.0238360899 -0.0289451024
## PctTeen2Par . . . .
## PctWorkMomYoungKids . . . .
## PctWorkMom -0.0717707203 -0.0748508293 -0.0776641284 -0.0825220681
## NumIlleg . . . .
## PctIlleg 0.1912146984 0.1879897695 0.1837869251 0.1803117490
## NumImmig -0.0467571385 -0.0563380792 -0.0660013358 -0.0752074022
## PctImmigRecent . . . .
## PctImmigRec5 . . . .
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 . . . .
## PctRecImmig10 0.0112162226 0.0105080734 0.0117160840 0.0138962783
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell . . . .
## PctLargHouseFam . . . .
## PctLargHouseOccup . . . .
## PersPerOccupHous . . . .
## PersPerOwnOccHous . . . .
## PersPerRentOccHous . . . .
## PctPersOwnOccup . . -0.0007118666 -0.0015972707
## PctPersDenseHous 0.1179146648 0.1208236619 0.1253001799 0.1264237356
## PctHousLess3BR 0.0099351532 0.0094355665 0.0104472229 0.0104540795
## MedNumBR . . . .
## HousVacant 0.1010192925 0.1018094582 0.1031758701 0.1042229001
## PctHousOccup -0.0587099126 -0.0597903385 -0.0605996993 -0.0620501687
## PctHousOwnOcc . . . .
## PctVacantBoarded 0.0432324753 0.0437644590 0.0443541489 0.0449886111
## PctVacMore6Mos -0.0164946752 -0.0186773385 -0.0216572468 -0.0245352448
## MedYrHousBuilt . -0.0011976285 -0.0026068424 -0.0035612113
## PctHousNoPhone . . . .
## PctWOFullPlumb . . . .
## OwnOccLowQuart . . . .
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ -0.0199612428 -0.0291857583 -0.0490639663 -0.0673546198
## RentMedian . . . .
## RentHighQ . . . .
## MedRent . 0.0042816331 0.0217012451 0.0392089377
## MedRentPctHousInc 0.0239826998 0.0280456440 0.0308890021 0.0332379172
## MedOwnCostPctInc . . . .
## MedOwnCostPctIncNoMtg -0.0432324133 -0.0463704012 -0.0497474330 -0.0534039983
## NumInShelters 0.0363958639 0.0393299070 0.0409859355 0.0432301613
## NumStreet 0.1653149320 0.1672610269 0.1692560879 0.1712192849
## PctForeignBorn 0.0184706945 0.0203140369 0.0189788491 0.0188017142
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 0.0166177973 0.0169651111 0.0171611311 0.0174616384
## PctSameState85 . . . .
## LandArea . . . .
## PopDens . . . .
## PctUsePubTrans . . . .
##
## (Intercept) 0.4914211903 5.089766e-01 0.5232527144 0.5402016525
## (Intercept) . . . .
## state -0.0008161695 -8.132500e-04 -0.0008147154 -0.0008188901
## fold -0.0015114943 -1.541044e-03 -0.0015727505 -0.0016000500
## population . . . .
## householdsize . . 0.0003019397 0.0037445566
## racepctblack 0.1696433892 1.721328e-01 0.1768728478 0.1811957122
## racePctWhite -0.0271169710 -2.795420e-02 -0.0270828314 -0.0263583723
## racePctAsian . . . .
## racePctHisp 0.0002560213 3.096418e-03 0.0049226163 0.0076274518
## agePct12t21 . . . .
## agePct12t29 -0.0848134709 -9.371704e-02 -0.1057851110 -0.1185058862
## agePct16t24 . . . .
## agePct65up . . . .
## numbUrban . . . .
## pctUrban 0.0349165106 3.463083e-02 0.0348870704 0.0350430097
## medIncome . . . .
## pctWWage -0.0417113681 -4.972244e-02 -0.0572570475 -0.0673664277
## pctWFarmSelf 0.0124427964 1.493412e-02 0.0167534041 0.0185337280
## pctWInvInc -0.0655956098 -6.779015e-02 -0.0714500363 -0.0758966303
## pctWSocSec 0.0058705077 9.223492e-03 0.0114223881 0.0117701621
## pctWPubAsst . . . .
## pctWRetire -0.0537567869 -5.890686e-02 -0.0629083730 -0.0663603725
## medFamInc . . . .
## perCapInc . . . .
## whitePerCap -0.0227778012 -3.321007e-02 -0.0408318858 -0.0452441728
## blackPerCap -0.0149149552 -1.589630e-02 -0.0166660926 -0.0171730563
## indianPerCap -0.0225581618 -2.333868e-02 -0.0238528168 -0.0242568561
## AsianPerCap 0.0187829757 1.959184e-02 0.0201241297 0.0206629500
## OtherPerCap 0.0372929862 3.765145e-02 0.0382058426 0.0386303262
## HispPerCap 0.0069367126 9.451797e-03 0.0115112574 0.0137184050
## NumUnderPov . . . .
## PctPopUnderPov -0.0746361006 -8.197919e-02 -0.0907521989 -0.0980223205
## PctLess9thGrade -0.0013437282 -6.518866e-03 -0.0126813612 -0.0182606415
## PctNotHSGrad . . . .
## PctBSorMore . . . .
## PctUnemployed -0.0104379268 -1.320054e-02 -0.0147670958 -0.0163476844
## PctEmploy 0.0192451794 2.803823e-02 0.0378849741 0.0485384326
## PctEmplManu -0.0130681304 -1.306134e-02 -0.0143811641 -0.0156778300
## PctEmplProfServ . . . .
## PctOccupManu . . . .
## PctOccupMgmtProf . . . .
## MalePctDivorce 0.0960615405 9.363046e-02 0.0948629994 0.1007142350
## MalePctNevMarr 0.0361293913 4.474061e-02 0.0562361635 0.0663960179
## FemalePctDiv . . -0.0069053285 -0.0197785203
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -0.2329441326 -2.335516e-01 -0.2305686713 -0.2314596895
## PctYoungKids2Par -0.0313409057 -3.216130e-02 -0.0343409708 -0.0364173342
## PctTeen2Par . . . .
## PctWorkMomYoungKids . . . .
## PctWorkMom -0.0883610877 -9.332040e-02 -0.0980754544 -0.1018771139
## NumIlleg -0.0015795392 -1.588451e-02 -0.0254909803 -0.0350095997
## PctIlleg 0.1758842876 1.757083e-01 0.1738538915 0.1700096644
## NumImmig -0.0816396414 -8.568639e-02 -0.0900697054 -0.0935563564
## PctImmigRecent . . . .
## PctImmigRec5 . -2.111165e-05 -0.0007209807 -0.0010468397
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 . . . .
## PctRecImmig10 0.0134866971 1.105760e-02 0.0116622149 0.0124843152
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell . . . .
## PctLargHouseFam . . . .
## PctLargHouseOccup . . . .
## PersPerOccupHous . . 0.0007490883 0.0047537756
## PersPerOwnOccHous . . . .
## PersPerRentOccHous . . . .
## PctPersOwnOccup -0.0061307950 -1.002433e-02 -0.0148412984 -0.0213550843
## PctPersDenseHous 0.1272908067 1.280583e-01 0.1283728990 0.1249357590
## PctHousLess3BR 0.0083541698 7.388534e-03 0.0084691223 0.0115066039
## MedNumBR . . . .
## HousVacant 0.1052221289 1.109087e-01 0.1150182762 0.1193910178
## PctHousOccup -0.0638940311 -6.376180e-02 -0.0624243306 -0.0609902113
## PctHousOwnOcc . . . .
## PctVacantBoarded 0.0455095912 4.652153e-02 0.0472601950 0.0476869456
## PctVacMore6Mos -0.0272965626 -2.938216e-02 -0.0317305617 -0.0341478515
## MedYrHousBuilt -0.0040354649 -3.986581e-03 -0.0049459068 -0.0056359786
## PctHousNoPhone . 2.338124e-04 0.0056060295 0.0092502076
## PctWOFullPlumb . . . .
## OwnOccLowQuart -0.0042160612 -8.378395e-03 -0.0133789421 -0.0187654962
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ -0.0863136677 -1.016538e-01 -0.1157127451 -0.1272733009
## RentMedian . . . .
## RentHighQ . . . .
## MedRent 0.0612195519 8.190847e-02 0.1001005191 0.1150791483
## MedRentPctHousInc 0.0353764652 3.766725e-02 0.0405199897 0.0435063909
## MedOwnCostPctInc -0.0020922511 -7.244814e-03 -0.0109827583 -0.0149636604
## MedOwnCostPctIncNoMtg -0.0563739031 -5.839299e-02 -0.0604972218 -0.0626143356
## NumInShelters 0.0449606945 5.018988e-02 0.0557658837 0.0600979010
## NumStreet 0.1730641117 1.754200e-01 0.1768381214 0.1782382367
## PctForeignBorn 0.0208448061 2.427390e-02 0.0269951588 0.0288697544
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 0.0181943159 1.860673e-02 0.0193528269 0.0202791905
## PctSameState85 . . . .
## LandArea . . . .
## PopDens . . . .
## PctUsePubTrans . -3.161518e-04 -0.0037546881 -0.0066115234
##
## (Intercept) 0.556834824 5.697581e-01 0.5793014436 5.840577e-01
## (Intercept) . . . .
## state -0.000824504 -8.302962e-04 -0.0008282230 -8.274427e-04
## fold -0.001626152 -1.646556e-03 -0.0016690621 -1.686548e-03
## population . . . .
## householdsize 0.007423135 1.004444e-02 0.0146675670 1.724499e-02
## racepctblack 0.184323995 1.862461e-01 0.1865809048 1.879479e-01
## racePctWhite -0.026661327 -2.851002e-02 -0.0308847546 -3.190789e-02
## racePctAsian . . . .
## racePctHisp 0.010557151 1.351425e-02 0.0149655630 1.696581e-02
## agePct12t21 0.002143208 1.224598e-02 0.0189418740 2.419845e-02
## agePct12t29 -0.132734217 -1.540542e-01 -0.1717769177 -1.850680e-01
## agePct16t24 . . . .
## agePct65up . . 0.0001149393 5.059345e-03
## numbUrban . -1.209772e-03 -0.0053381149 -9.766360e-03
## pctUrban 0.035330227 3.575345e-02 0.0362127717 3.671268e-02
## medIncome . . . .
## pctWWage -0.078198362 -8.632610e-02 -0.0948423945 -1.014485e-01
## pctWFarmSelf 0.019955234 2.143952e-02 0.0232624944 2.480850e-02
## pctWInvInc -0.080304519 -8.475446e-02 -0.0867773433 -8.911587e-02
## pctWSocSec 0.012132782 1.407931e-02 0.0169372764 1.803322e-02
## pctWPubAsst . . . .
## pctWRetire -0.069540863 -7.184448e-02 -0.0744725359 -7.764970e-02
## medFamInc . . . .
## perCapInc . . . .
## whitePerCap -0.048806562 -5.262569e-02 -0.0564218065 -5.966396e-02
## blackPerCap -0.017748079 -1.843241e-02 -0.0189999077 -1.939436e-02
## indianPerCap -0.024589690 -2.495286e-02 -0.0252161295 -2.546606e-02
## AsianPerCap 0.021206330 2.177364e-02 0.0224177195 2.296683e-02
## OtherPerCap 0.039096583 3.941744e-02 0.0398153172 4.018888e-02
## HispPerCap 0.015721767 1.759589e-02 0.0193366866 2.088545e-02
## NumUnderPov . . . .
## PctPopUnderPov -0.104136241 -1.095520e-01 -0.1140686441 -1.176338e-01
## PctLess9thGrade -0.023494958 -2.827185e-02 -0.0345749259 -4.023551e-02
## PctNotHSGrad . . . .
## PctBSorMore . . . 1.391122e-04
## PctUnemployed -0.017231290 -1.750846e-02 -0.0174139184 -1.666526e-02
## PctEmploy 0.060445882 7.310291e-02 0.0858523674 9.682538e-02
## PctEmplManu -0.016810988 -1.836000e-02 -0.0208021921 -2.255431e-02
## PctEmplProfServ . . . .
## PctOccupManu . 1.346640e-03 0.0046261686 7.108888e-03
## PctOccupMgmtProf . . . .
## MalePctDivorce 0.107732136 1.152398e-01 0.1208621311 1.266295e-01
## MalePctNevMarr 0.076171099 8.597559e-02 0.0964565336 1.054700e-01
## FemalePctDiv -0.033166486 -4.552063e-02 -0.0558934016 -6.506595e-02
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -0.233046720 -2.338313e-01 -0.2381526661 -2.408447e-01
## PctYoungKids2Par -0.037281541 -3.680902e-02 -0.0355963644 -3.427680e-02
## PctTeen2Par . . . .
## PctWorkMomYoungKids . . . .
## PctWorkMom -0.105403028 -1.093346e-01 -0.1134650066 -1.168149e-01
## NumIlleg -0.042982512 -5.009782e-02 -0.0569153353 -6.221127e-02
## PctIlleg 0.166131708 1.635443e-01 0.1618669105 1.605178e-01
## NumImmig -0.096265986 -9.810651e-02 -0.0988477953 -9.982598e-02
## PctImmigRecent . . . .
## PctImmigRec5 -0.001246827 -1.458470e-03 -0.0013254871 -1.443556e-03
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 . . . .
## PctRecImmig10 0.013055024 1.348307e-02 0.0137750366 1.433103e-02
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell . . . -5.599565e-04
## PctLargHouseFam . -4.570750e-03 -0.0177865432 -2.834740e-02
## PctLargHouseOccup . . . -2.174459e-06
## PersPerOccupHous 0.007931505 1.220729e-02 0.0205266262 3.004547e-02
## PersPerOwnOccHous . . . .
## PersPerRentOccHous . . . .
## PctPersOwnOccup -0.028298449 -3.577309e-02 -0.0403722332 -4.528542e-02
## PctPersDenseHous 0.120914416 1.185666e-01 0.1232507896 1.271090e-01
## PctHousLess3BR 0.013948023 1.723298e-02 0.0210607723 2.329566e-02
## MedNumBR . . . .
## HousVacant 0.123193526 1.274867e-01 0.1329656500 1.365052e-01
## PctHousOccup -0.059445167 -5.799251e-02 -0.0568802943 -5.585424e-02
## PctHousOwnOcc . . . .
## PctVacantBoarded 0.047879358 4.812779e-02 0.0486928206 4.910958e-02
## PctVacMore6Mos -0.036335222 -3.859766e-02 -0.0408755721 -4.272128e-02
## MedYrHousBuilt -0.005995409 -6.629567e-03 -0.0076074892 -8.547952e-03
## PctHousNoPhone 0.012358064 1.483078e-02 0.0174353130 1.928894e-02
## PctWOFullPlumb . -4.728094e-05 -0.0013195050 -2.507654e-03
## OwnOccLowQuart -0.024212998 -2.982638e-02 -0.0344602295 -3.807265e-02
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ -0.138870624 -1.490333e-01 -0.1578210266 -1.652819e-01
## RentMedian . . . .
## RentHighQ . . . .
## MedRent 0.129743904 1.440134e-01 0.1556519818 1.652423e-01
## MedRentPctHousInc 0.046020368 4.775178e-02 0.0486572641 4.950079e-02
## MedOwnCostPctInc -0.018379815 -2.111580e-02 -0.0233092397 -2.541325e-02
## MedOwnCostPctIncNoMtg -0.064545070 -6.608510e-02 -0.0672323703 -6.844096e-02
## NumInShelters 0.063261146 6.668756e-02 0.0702641393 7.396783e-02
## NumStreet 0.179351038 1.801051e-01 0.1811531022 1.820691e-01
## PctForeignBorn 0.030566744 3.182539e-02 0.0322815470 3.243261e-02
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 0.021096491 2.180302e-02 0.0229460091 2.349009e-02
## PctSameState85 . . . .
## LandArea . . 0.0007882646 3.445212e-03
## PopDens . . . .
## PctUsePubTrans -0.009131058 -1.129408e-02 -0.0130463535 -1.451418e-02
##
## (Intercept) 5.822872e-01 5.753725e-01 0.5741139446 0.5805356903
## (Intercept) . . . .
## state -8.199176e-04 -8.151324e-04 -0.0008050362 -0.0007978003
## fold -1.698180e-03 -1.701235e-03 -0.0016988577 -0.0017040090
## population . . . .
## householdsize 1.933590e-02 1.997993e-02 0.0161030318 0.0143767087
## racepctblack 1.891697e-01 1.924652e-01 0.1956545568 0.1961716942
## racePctWhite -3.139531e-02 -2.903396e-02 -0.0268935811 -0.0275107056
## racePctAsian . . . .
## racePctHisp 2.151145e-02 2.712450e-02 0.0340294438 0.0367404145
## agePct12t21 3.026783e-02 3.300840e-02 0.0348251542 0.0371592813
## agePct12t29 -2.009530e-01 -2.124288e-01 -0.2231776675 -0.2313994717
## agePct16t24 . . . .
## agePct65up 8.785035e-03 8.874084e-03 0.0090513532 0.0109318801
## numbUrban -1.591703e-02 -2.094103e-02 -0.0249468244 -0.0291380769
## pctUrban 3.728249e-02 3.785857e-02 0.0386042085 0.0390903401
## medIncome . . . .
## pctWWage -1.127855e-01 -1.220755e-01 -0.1306419257 -0.1371188338
## pctWFarmSelf 2.657062e-02 2.802182e-02 0.0296296595 0.0311307590
## pctWInvInc -9.591178e-02 -1.018555e-01 -0.1104810303 -0.1165252689
## pctWSocSec 2.157348e-02 2.852832e-02 0.0354295340 0.0370399116
## pctWPubAsst . . . .
## pctWRetire -7.841896e-02 -7.877167e-02 -0.0790373589 -0.0799494917
## medFamInc . 2.517363e-05 0.0155125082 0.0272513684
## perCapInc . . . .
## whitePerCap -6.670471e-02 -7.315029e-02 -0.0875569067 -0.1011046199
## blackPerCap -1.997242e-02 -2.026455e-02 -0.0211988724 -0.0222333953
## indianPerCap -2.581620e-02 -2.608577e-02 -0.0264579622 -0.0269142939
## AsianPerCap 2.352506e-02 2.389378e-02 0.0239540030 0.0239149825
## OtherPerCap 4.078481e-02 4.122199e-02 0.0416787497 0.0420088181
## HispPerCap 2.194357e-02 2.285806e-02 0.0232639676 0.0239533251
## NumUnderPov . . . .
## PctPopUnderPov -1.221637e-01 -1.265689e-01 -0.1296934316 -0.1341452743
## PctLess9thGrade -4.385866e-02 -4.566432e-02 -0.0468589608 -0.0491885298
## PctNotHSGrad . . . .
## PctBSorMore 1.051043e-02 2.126048e-02 0.0317788143 0.0368489742
## PctUnemployed -1.529848e-02 -1.410240e-02 -0.0128446793 -0.0128270688
## PctEmploy 1.131849e-01 1.259069e-01 0.1355576681 0.1425945807
## PctEmplManu -2.450373e-02 -2.673841e-02 -0.0295303002 -0.0320433474
## PctEmplProfServ . . . .
## PctOccupManu 1.124996e-02 1.564707e-02 0.0210789382 0.0264321844
## PctOccupMgmtProf . . 0.0004936109 0.0054724236
## MalePctDivorce 1.365525e-01 1.463284e-01 0.1536557308 0.1586098715
## MalePctNevMarr 1.162798e-01 1.262242e-01 0.1357276339 0.1413228457
## FemalePctDiv -7.753579e-02 -8.787823e-02 -0.0970980555 -0.1052066860
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -2.462675e-01 -2.474849e-01 -0.2479655163 -0.2534058209
## PctYoungKids2Par -3.240358e-02 -3.164669e-02 -0.0319482648 -0.0316088959
## PctTeen2Par . . . .
## PctWorkMomYoungKids . 3.575735e-04 0.0058657389 0.0101342443
## PctWorkMom -1.206284e-01 -1.239671e-01 -0.1303043258 -0.1360160931
## NumIlleg -6.610603e-02 -6.914788e-02 -0.0686144628 -0.0703568958
## PctIlleg 1.586057e-01 1.568128e-01 0.1531367116 0.1504172587
## NumImmig -9.950434e-02 -9.967879e-02 -0.1007481179 -0.1018474845
## PctImmigRecent . . . .
## PctImmigRec5 -1.607990e-03 -2.129246e-03 -0.0018770158 -0.0019589704
## PctImmigRec8 . . . .
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 2.569853e-05 6.289237e-03 0.0084162808 0.0121482843
## PctRecImmig10 1.643737e-02 1.349215e-02 0.0115865905 0.0073595556
## PctSpeakEnglOnly . . . .
## PctNotSpeakEnglWell -9.311398e-03 -2.071641e-02 -0.0369417957 -0.0433482083
## PctLargHouseFam -4.348623e-02 -5.622283e-02 -0.0595679488 -0.0603197650
## PctLargHouseOccup -1.025806e-04 -1.754620e-04 -0.0081959542 -0.0148749284
## PersPerOccupHous 4.716075e-02 6.786149e-02 0.1229028930 0.1580680475
## PersPerOwnOccHous -3.066892e-05 -2.368124e-03 -0.0279886659 -0.0449488190
## PersPerRentOccHous . -2.257811e-03 -0.0183427824 -0.0290009871
## PctPersOwnOccup -5.028085e-02 -5.618339e-02 -0.0687314684 -0.0764541753
## PctPersDenseHous 1.350166e-01 1.410151e-01 0.1470200300 0.1506684124
## PctHousLess3BR 2.745311e-02 3.097674e-02 0.0360352221 0.0404172699
## MedNumBR . 8.041263e-04 0.0028870743 0.0045165918
## HousVacant 1.415893e-01 1.454959e-01 0.1474526885 0.1510753802
## PctHousOccup -5.451897e-02 -5.408864e-02 -0.0543852690 -0.0542893429
## PctHousOwnOcc . . . .
## PctVacantBoarded 4.962442e-02 5.015913e-02 0.0512124976 0.0519682656
## PctVacMore6Mos -4.495348e-02 -4.700972e-02 -0.0490167622 -0.0506453188
## MedYrHousBuilt -9.021263e-03 -9.121462e-03 -0.0091977074 -0.0095195354
## PctHousNoPhone 1.973440e-02 2.020212e-02 0.0205079140 0.0211912317
## PctWOFullPlumb -3.647853e-03 -4.437145e-03 -0.0049280738 -0.0055017139
## OwnOccLowQuart -4.275646e-02 -4.777755e-02 -0.0564222153 -0.0617737715
## OwnOccMedVal . . . .
## OwnOccHiQuart . . . .
## RentLowQ -1.737906e-01 -1.801525e-01 -0.1853198094 -0.1895356165
## RentMedian . . . .
## RentHighQ . . . .
## MedRent 1.764234e-01 1.853036e-01 0.1938667612 0.2009483112
## MedRentPctHousInc 4.945060e-02 4.951001e-02 0.0481686012 0.0478496060
## MedOwnCostPctInc -2.747286e-02 -2.929504e-02 -0.0296001304 -0.0305097164
## MedOwnCostPctIncNoMtg -6.908225e-02 -6.997734e-02 -0.0712135601 -0.0717042728
## NumInShelters 7.738241e-02 8.163061e-02 0.0860607188 0.0893355438
## NumStreet 1.825606e-01 1.826236e-01 0.1823450634 0.1827054476
## PctForeignBorn 3.445977e-02 3.861615e-02 0.0488006410 0.0540548604
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 2.489721e-02 2.545015e-02 0.0258300758 0.0260060338
## PctSameState85 . 1.593011e-03 0.0032545997 0.0045087398
## LandArea 5.384246e-03 6.934200e-03 0.0086779347 0.0102068420
## PopDens . . . .
## PctUsePubTrans -1.633618e-02 -1.837944e-02 -0.0208251679 -0.0228053956
##
## (Intercept) 5.834766e-01 0.5867939833 0.5891368148 0.5912861860
## (Intercept) . . . .
## state -7.909477e-04 -0.0007858794 -0.0007806395 -0.0007731370
## fold -1.707660e-03 -0.0017100313 -0.0017130955 -0.0017153592
## population . . . .
## householdsize 1.250944e-02 0.0109853844 0.0094868329 0.0068544101
## racepctblack 1.972102e-01 0.1978777359 0.1984823282 0.1998046417
## racePctWhite -2.757767e-02 -0.0279480711 -0.0281623042 -0.0281460015
## racePctAsian . . . .
## racePctHisp 3.968366e-02 0.0421725769 0.0445627363 0.0474647494
## agePct12t21 3.887144e-02 0.0407171466 0.0421361388 0.0417246540
## agePct12t29 -2.384784e-01 -0.2451626702 -0.2508080740 -0.2542710696
## agePct16t24 . . . .
## agePct65up 1.262499e-02 0.0141380334 0.0156289950 0.0165002062
## numbUrban -3.319577e-02 -0.0368177420 -0.0403354875 -0.0430758236
## pctUrban 3.958776e-02 0.0400617425 0.0404950422 0.0408777877
## medIncome . . . .
## pctWWage -1.435532e-01 -0.1487669827 -0.1536923855 -0.1586741716
## pctWFarmSelf 3.248282e-02 0.0336520363 0.0347583073 0.0357866572
## pctWInvInc -1.219396e-01 -0.1267180313 -0.1310729653 -0.1353148359
## pctWSocSec 3.927297e-02 0.0414632333 0.0436425404 0.0469705549
## pctWPubAsst . . . .
## pctWRetire -8.072193e-02 -0.0814707917 -0.0821092834 -0.0827025770
## medFamInc 3.962652e-02 0.0502009501 0.0603929017 0.0728161169
## perCapInc . . . .
## whitePerCap -1.136289e-01 -0.1246292766 -0.1348951520 -0.1489006610
## blackPerCap -2.315912e-02 -0.0239358980 -0.0246614266 -0.0252797754
## indianPerCap -2.730768e-02 -0.0276577806 -0.0279677724 -0.0283366850
## AsianPerCap 2.386254e-02 0.0238124005 0.0237732537 0.0236448056
## OtherPerCap 4.235588e-02 0.0426492109 0.0429480342 0.0433315843
## HispPerCap 2.446142e-02 0.0249296609 0.0253116705 0.0257099281
## NumUnderPov . . . .
## PctPopUnderPov -1.371964e-01 -0.1403779045 -0.1429794643 -0.1443559667
## PctLess9thGrade -5.131514e-02 -0.0531177249 -0.0547521333 -0.0565692875
## PctNotHSGrad . . . .
## PctBSorMore 4.019921e-02 0.0431119096 0.0455447690 0.0480357397
## PctUnemployed -1.259370e-02 -0.0123550179 -0.0120583502 -0.0118775190
## PctEmploy 1.499009e-01 0.1562679486 0.1623518567 0.1680803601
## PctEmplManu -3.451071e-02 -0.0366996818 -0.0387448061 -0.0404816174
## PctEmplProfServ . . . .
## PctOccupManu 3.182499e-02 0.0366284486 0.0411758434 0.0447249328
## PctOccupMgmtProf 1.120492e-02 0.0162660525 0.0213073505 0.0257992422
## MalePctDivorce 1.632954e-01 0.1673019144 0.1709900120 0.1747095796
## MalePctNevMarr 1.469871e-01 0.1520612130 0.1566579274 0.1604508139
## FemalePctDiv -1.124545e-01 -0.1188392063 -0.1247099916 -0.1303890136
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -2.573646e-01 -0.2609602081 -0.2644481597 -0.2685197666
## PctYoungKids2Par -3.133247e-02 -0.0311486612 -0.0309198395 -0.0307633066
## PctTeen2Par . . . .
## PctWorkMomYoungKids 1.407451e-02 0.0175615502 0.0207583814 0.0235983238
## PctWorkMom -1.411327e-01 -0.1457818573 -0.1500177610 -0.1533281535
## NumIlleg -7.159431e-02 -0.0727498912 -0.0737810155 -0.0743748761
## PctIlleg 1.478350e-01 0.1454842368 0.1433908239 0.1410586037
## NumImmig -1.027215e-01 -0.1036392364 -0.1044714295 -0.1058320986
## PctImmigRecent 4.471176e-05 0.0018233948 0.0032946784 0.0046337862
## PctImmigRec5 -2.077574e-03 -0.0036430717 -0.0046479729 -0.0054621124
## PctImmigRec8 -4.357149e-05 -0.0004765115 -0.0011036506 -0.0016690193
## PctImmigRec10 . . . .
## PctRecentImmig . . . .
## PctRecImmig5 . . . .
## PctRecImmig8 1.660203e-02 0.0203701026 0.0215598879 0.0229541439
## PctRecImmig10 2.743578e-03 . . .
## PctSpeakEnglOnly . . . -0.0001200048
## PctNotSpeakEnglWell -5.036980e-02 -0.0564707285 -0.0624933799 -0.0680036040
## PctLargHouseFam -6.181636e-02 -0.0632954934 -0.0651266917 -0.0656429932
## PctLargHouseOccup -2.082054e-02 -0.0257936939 -0.0301993808 -0.0361164868
## PersPerOccupHous 1.920090e-01 0.2207988365 0.2474425169 0.2777697574
## PersPerOwnOccHous -6.114100e-02 -0.0750911584 -0.0877581372 -0.1011099589
## PersPerRentOccHous -3.911534e-02 -0.0478297447 -0.0558339737 -0.0641177839
## PctPersOwnOccup -8.392756e-02 -0.0904661539 -0.0964165521 -0.1022806322
## PctPersDenseHous 1.547051e-01 0.1583895153 0.1621016197 0.1642481970
## PctHousLess3BR 4.448243e-02 0.0478034348 0.0508470630 0.0545556185
## MedNumBR 6.052874e-03 0.0073570029 0.0085751742 0.0098109111
## HousVacant 1.542888e-01 0.1571483999 0.1598662710 0.1624228906
## PctHousOccup -5.427276e-02 -0.0542942644 -0.0542889372 -0.0541496455
## PctHousOwnOcc . . . .
## PctVacantBoarded 5.269332e-02 0.0533726447 0.0540267405 0.0545245506
## PctVacMore6Mos -5.216306e-02 -0.0535339044 -0.0547946174 -0.0561627483
## MedYrHousBuilt -9.780775e-03 -0.0099512256 -0.0101086443 -0.0103514737
## PctHousNoPhone 2.167701e-02 0.0223358029 0.0227821792 0.0225744292
## PctWOFullPlumb -6.026911e-03 -0.0065138077 -0.0069610700 -0.0074524571
## OwnOccLowQuart -6.730323e-02 -0.0721842596 -0.0766408763 -0.0874580435
## OwnOccMedVal . . . .
## OwnOccHiQuart . . 0.0001601975 0.0084336425
## RentLowQ -1.937775e-01 -0.1974997576 -0.2011695717 -0.2041314430
## RentMedian . . . .
## RentHighQ . . . .
## MedRent 2.076489e-01 0.2137257248 0.2192846689 0.2235687206
## MedRentPctHousInc 4.743488e-02 0.0470860508 0.0466987224 0.0458548351
## MedOwnCostPctInc -3.112988e-02 -0.0316079709 -0.0320122108 -0.0325799255
## MedOwnCostPctIncNoMtg -7.231411e-02 -0.0727961461 -0.0732437555 -0.0736285487
## NumInShelters 9.256008e-02 0.0954364773 0.0981722297 0.1006916919
## NumStreet 1.829500e-01 0.1831881470 0.1833908489 0.1833567778
## PctForeignBorn 5.930631e-02 0.0627223555 0.0658182457 0.0686471608
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 2.609889e-02 0.0261728386 0.0261952813 0.0263025829
## PctSameState85 5.669199e-03 0.0067659166 0.0077252603 0.0086347154
## LandArea 1.156911e-02 0.0128662561 0.0140812152 0.0147787375
## PopDens . . -0.0001285819 -0.0007612172
## PctUsePubTrans -2.464636e-02 -0.0262528417 -0.0276656631 -0.0289284126
##
## (Intercept) 5.967815e-01 0.5996560580 0.6079054883 0.6148287732
## (Intercept) . . . .
## state -7.708544e-04 -0.0007707348 -0.0007694075 -0.0007672638
## fold -1.715289e-03 -0.0017125517 -0.0017128721 -0.0017154207
## population . . . .
## householdsize 5.074862e-03 0.0029745336 0.0014339567 .
## racepctblack 2.012796e-01 0.2025092256 0.2034671816 0.2037642514
## racePctWhite -2.786279e-02 -0.0285217066 -0.0292414452 -0.0302518379
## racePctAsian -1.323125e-04 -0.0012641983 -0.0019366805 -0.0026488523
## racePctHisp 4.749734e-02 0.0468193981 0.0470527405 0.0477215590
## agePct12t21 4.224029e-02 0.0442639977 0.0470876802 0.0488435838
## agePct12t29 -2.585841e-01 -0.2639553948 -0.2710285517 -0.2764660587
## agePct16t24 . . . .
## agePct65up 1.815060e-02 0.0207767904 0.0216778337 0.0206076311
## numbUrban -4.572852e-02 -0.0478852524 -0.0509818370 -0.0562733751
## pctUrban 4.118981e-02 0.0415182827 0.0417967978 0.0421117822
## medIncome . . . .
## pctWWage -1.615820e-01 -0.1632405864 -0.1676817230 -0.1713322680
## pctWFarmSelf 3.657048e-02 0.0373555687 0.0382686540 0.0391332558
## pctWInvInc -1.383664e-01 -0.1382527011 -0.1388837694 -0.1400242523
## pctWSocSec 4.916489e-02 0.0481908910 0.0478085246 0.0496663441
## pctWPubAsst . . . .
## pctWRetire -8.322096e-02 -0.0838425371 -0.0843252137 -0.0847167918
## medFamInc 8.249584e-02 0.0871730735 0.0921573888 0.0966800174
## perCapInc . . . .
## whitePerCap -1.607642e-01 -0.1697328514 -0.1793178219 -0.1888923800
## blackPerCap -2.570340e-02 -0.0260820337 -0.0265858479 -0.0270725951
## indianPerCap -2.865669e-02 -0.0289081732 -0.0291310998 -0.0293076818
## AsianPerCap 2.363356e-02 0.0235234644 0.0234401745 0.0233770443
## OtherPerCap 4.354743e-02 0.0437287905 0.0439137028 0.0440809960
## HispPerCap 2.619148e-02 0.0265581276 0.0268860012 0.0271235603
## NumUnderPov . 0.0001855345 0.0107248911 0.0218697940
## PctPopUnderPov -1.462755e-01 -0.1485240264 -0.1512285571 -0.1540255953
## PctLess9thGrade -5.872286e-02 -0.0664527066 -0.0738581174 -0.0788175373
## PctNotHSGrad 6.874279e-05 0.0106390672 0.0196200358 0.0251715232
## PctBSorMore 4.998593e-02 0.0512555069 0.0525837604 0.0542904207
## PctUnemployed -1.174318e-02 -0.0112238614 -0.0104661929 -0.0100317017
## PctEmploy 1.728134e-01 0.1772982251 0.1830817491 0.1874531189
## PctEmplManu -4.202929e-02 -0.0439635633 -0.0455882119 -0.0474780842
## PctEmplProfServ . . -0.0018447234 -0.0042938983
## PctOccupManu 4.797280e-02 0.0509487903 0.0532769605 0.0561750621
## PctOccupMgmtProf 2.936459e-02 0.0338355340 0.0385443505 0.0441890200
## MalePctDivorce 1.777082e-01 0.1795959924 0.1808688745 0.1822422239
## MalePctNevMarr 1.638927e-01 0.1674348173 0.1712115882 0.1742083635
## FemalePctDiv -1.344149e-01 -0.1368461997 -0.1404201290 -0.1441837054
## TotalPctDiv . . . .
## PersPerFam . . . .
## PctFam2Par . . . .
## PctKids2Par -2.714519e-01 -0.2703663468 -0.2705908632 -0.2721383190
## PctYoungKids2Par -3.054176e-02 -0.0313305990 -0.0315993968 -0.0314462252
## PctTeen2Par . -0.0001062522 -0.0012331102 -0.0020507280
## PctWorkMomYoungKids 2.596743e-02 0.0281240276 0.0310334897 0.0333817325
## PctWorkMom -1.563972e-01 -0.1591830502 -0.1622777874 -0.1647300099
## NumIlleg -7.483678e-02 -0.0759601581 -0.0824995034 -0.0892009690
## PctIlleg 1.394387e-01 0.1376070597 0.1358162485 0.1343831071
## NumImmig -1.071073e-01 -0.1075061893 -0.1103631491 -0.1124394789
## PctImmigRecent 5.861491e-03 0.0069294451 0.0077129803 0.0088042375
## PctImmigRec5 -6.196790e-03 -0.0068507747 -0.0070185257 -0.0068660761
## PctImmigRec8 -2.194220e-03 -0.0027845258 -0.0033009262 -0.0040441098
## PctImmigRec10 . . . .
## PctRecentImmig . . . -0.0025697130
## PctRecImmig5 . . . .
## PctRecImmig8 2.531770e-02 0.0273396479 0.0288515895 0.0313489260
## PctRecImmig10 . . . .
## PctSpeakEnglOnly -5.508709e-03 -0.0098362401 -0.0133249057 -0.0149516634
## PctNotSpeakEnglWell -7.246095e-02 -0.0761584377 -0.0808118307 -0.0855625025
## PctLargHouseFam -6.590946e-02 -0.0656944867 -0.0662232079 -0.0672897468
## PctLargHouseOccup -3.971961e-02 -0.0414458901 -0.0430869534 -0.0448707026
## PersPerOccupHous 3.008972e-01 0.3177296840 0.3357937368 0.3525525668
## PersPerOwnOccHous -1.120617e-01 -0.1210860096 -0.1307823103 -0.1392242299
## PersPerRentOccHous -7.036383e-02 -0.0756756295 -0.0827564055 -0.0890113535
## PctPersOwnOccup -1.069413e-01 -0.1113270211 -0.1164218002 -0.1211466141
## PctPersDenseHous 1.648976e-01 0.1655977035 0.1680112003 0.1705942066
## PctHousLess3BR 5.783758e-02 0.0592241874 0.0605524005 0.0620449355
## MedNumBR 1.089831e-02 0.0116922038 0.0124778033 0.0132629487
## HousVacant 1.646199e-01 0.1665815602 0.1652556487 0.1651308834
## PctHousOccup -5.375486e-02 -0.0533039083 -0.0533103077 -0.0531918127
## PctHousOwnOcc . . . .
## PctVacantBoarded 5.472918e-02 0.0550193409 0.0552080433 0.0555286175
## PctVacMore6Mos -5.737982e-02 -0.0584830864 -0.0593974607 -0.0602508107
## MedYrHousBuilt -1.037071e-02 -0.0104518189 -0.0106736233 -0.0111671910
## PctHousNoPhone 2.292876e-02 0.0234855710 0.0236961656 0.0238456439
## PctWOFullPlumb -7.795668e-03 -0.0080790107 -0.0085029372 -0.0089151445
## OwnOccLowQuart -9.880297e-02 -0.1073679609 -0.1177743558 -0.1274699672
## OwnOccMedVal . . . .
## OwnOccHiQuart 1.725492e-02 0.0246547286 0.0335498899 0.0417515200
## RentLowQ -2.067024e-01 -0.2083532427 -0.2106391591 -0.2126831284
## RentMedian . . . .
## RentHighQ . . . .
## MedRent 2.276497e-01 0.2312664747 0.2361581412 0.2406416503
## MedRentPctHousInc 4.567763e-02 0.0458109688 0.0455596116 0.0453310622
## MedOwnCostPctInc -3.325024e-02 -0.0340814452 -0.0350502600 -0.0358441302
## MedOwnCostPctIncNoMtg -7.414689e-02 -0.0746405728 -0.0748854842 -0.0751039666
## NumInShelters 1.028897e-01 0.1047290608 0.1059578470 0.1075377671
## NumStreet 1.832944e-01 0.1832715864 0.1836227460 0.1838180126
## PctForeignBorn 6.724566e-02 0.0664379633 0.0665032918 0.0690402500
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 2.612369e-02 0.0253374012 0.0247110677 0.0244073631
## PctSameState85 9.739081e-03 0.0107142545 0.0114749525 0.0121437906
## LandArea 1.559783e-02 0.0159705235 0.0163896973 0.0167169874
## PopDens -1.018222e-03 -0.0015558916 -0.0021002278 -0.0025982043
## PctUsePubTrans -3.002181e-02 -0.0311593201 -0.0321514189 -0.0330544859
##
## (Intercept) 0.6195961941 0.6234386319 0.6251888072 0.6307192693
## (Intercept) . . . .
## state -0.0007660077 -0.0007651289 -0.0007664733 -0.0007620868
## fold -0.0017176001 -0.0017182672 -0.0017219371 -0.0017169277
## population . . . .
## householdsize . . . .
## racepctblack 0.2041025191 0.2042435728 0.2043900760 0.2047006709
## racePctWhite -0.0308547433 -0.0314313910 -0.0318054192 -0.0325689794
## racePctAsian -0.0031030221 -0.0034453046 -0.0038301117 -0.0047050958
## racePctHisp 0.0487094908 0.0495175209 0.0493053180 0.0498528338
## agePct12t21 0.0495482073 0.0496932814 0.0494099702 0.0504857456
## agePct12t29 -0.2808733968 -0.2846111717 -0.2852541973 -0.2903687909
## agePct16t24 . . . .
## agePct65up 0.0197871321 0.0195371933 0.0201002479 0.0222135441
## numbUrban -0.0616097861 -0.0664531605 -0.0669318655 -0.0719864486
## pctUrban 0.0424127102 0.0426771720 0.0427211859 0.0429760009
## medIncome . . . .
## pctWWage -0.1738904353 -0.1764295157 -0.1769493636 -0.1803919422
## pctWFarmSelf 0.0398631902 0.0404990151 0.0407509558 0.0415730810
## pctWInvInc -0.1413809184 -0.1425561106 -0.1427849733 -0.1447443587
## pctWSocSec 0.0518468707 0.0536667634 0.0540028962 0.0536292087
## pctWPubAsst -0.0005408910 -0.0014623606 -0.0017477321 -0.0019686583
## pctWRetire -0.0849435767 -0.0850613310 -0.0853904104 -0.0855642622
## medFamInc 0.1014784341 0.1070608696 0.1081787472 0.1138370537
## perCapInc . . . .
## whitePerCap -0.1978500170 -0.2061490329 -0.2079874564 -0.2174806372
## blackPerCap -0.0274698893 -0.0278010946 -0.0278791571 -0.0284165594
## indianPerCap -0.0294811313 -0.0296639292 -0.0297559834 -0.0300326796
## AsianPerCap 0.0233187588 0.0232488987 0.0233409275 0.0231529989
## OtherPerCap 0.0442274071 0.0443502652 0.0444419216 0.0445712938
## HispPerCap 0.0273546197 0.0275457332 0.0277389533 0.0278361507
## NumUnderPov 0.0311930777 0.0394127866 0.0415176845 0.0532500318
## PctPopUnderPov -0.1560487402 -0.1577360933 -0.1586930089 -0.1616565019
## PctLess9thGrade -0.0815793328 -0.0837755540 -0.0849538723 -0.0901995726
## PctNotHSGrad 0.0279882543 0.0303137118 0.0318085970 0.0376988058
## PctBSorMore 0.0558271945 0.0572737986 0.0583818758 0.0622131259
## PctUnemployed -0.0094837285 -0.0088074200 -0.0087898481 -0.0079615216
## PctEmploy 0.1914126582 0.1954158442 0.1964646034 0.2019352785
## PctEmplManu -0.0491093089 -0.0505604819 -0.0509146832 -0.0523636865
## PctEmplProfServ -0.0062234992 -0.0078560062 -0.0082916784 -0.0100838211
## PctOccupManu 0.0588706390 0.0612181995 0.0614851152 0.0638267464
## PctOccupMgmtProf 0.0488666360 0.0528502753 0.0530895670 0.0565892455
## MalePctDivorce 0.1833964390 0.1844122708 0.1848208564 0.1865357432
## MalePctNevMarr 0.1767402393 0.1794294828 0.1804778486 0.1839669489
## FemalePctDiv -0.1473311035 -0.1499810090 -0.1508691804 -0.1543414867
## TotalPctDiv . . . .
## PersPerFam . -0.0001528718 -0.0006394668 -0.0030738307
## PctFam2Par . . . .
## PctKids2Par -0.2740094479 -0.2758934628 -0.2757785780 -0.2771479363
## PctYoungKids2Par -0.0314637396 -0.0314960546 -0.0317441521 -0.0319734472
## PctTeen2Par -0.0026659164 -0.0032434571 -0.0036727495 -0.0042140261
## PctWorkMomYoungKids 0.0352374040 0.0368170480 0.0373854030 0.0392762136
## PctWorkMom -0.1669720780 -0.1690475464 -0.1700286411 -0.1725766389
## NumIlleg -0.0947258526 -0.0993586357 -0.1010519657 -0.1081774713
## PctIlleg 0.1331142478 0.1319612424 0.1317127520 0.1303896292
## NumImmig -0.1142492295 -0.1158619304 -0.1171852394 -0.1190840495
## PctImmigRecent 0.0102740196 0.0117833071 0.0123963287 0.0145623405
## PctImmigRec5 -0.0071044548 -0.0074326042 -0.0076803801 -0.0079579608
## PctImmigRec8 -0.0047049216 -0.0054139169 -0.0058106175 -0.0071555737
## PctImmigRec10 . . . .
## PctRecentImmig -0.0063778231 -0.0103142427 -0.0115977161 -0.0186432968
## PctRecImmig5 . . . .
## PctRecImmig8 0.0347023575 0.0384619706 0.0399274300 0.0474211805
## PctRecImmig10 . . . .
## PctSpeakEnglOnly -0.0157713672 -0.0167159381 -0.0172470565 -0.0195192633
## PctNotSpeakEnglWell -0.0899259878 -0.0940889341 -0.0946635982 -0.0995551707
## PctLargHouseFam -0.0677101958 -0.0677383592 -0.0686243288 -0.0701635506
## PctLargHouseOccup -0.0472747149 -0.0498777846 -0.0501016851 -0.0508657095
## PersPerOccupHous 0.3664707269 0.3794467990 0.3825070382 0.3977245606
## PersPerOwnOccHous -0.1465594652 -0.1530239070 -0.1540609599 -0.1611506107
## PersPerRentOccHous -0.0942477193 -0.0987491518 -0.0994685427 -0.1047620384
## PctPersOwnOccup -0.1250967074 -0.1285140629 -0.1293759292 -0.1329131375
## PctPersDenseHous 0.1727379988 0.1747267530 0.1756499428 0.1790476596
## PctHousLess3BR 0.0635490191 0.0651436008 0.0654669759 0.0671945201
## MedNumBR 0.0140102212 0.0147314757 0.0150436891 0.0158459504
## HousVacant 0.1655132038 0.1657451726 0.1654667298 0.1646820383
## PctHousOccup -0.0530310008 -0.0528570982 -0.0529284895 -0.0527778229
## PctHousOwnOcc . . . .
## PctVacantBoarded 0.0558398401 0.0561125153 0.0561759150 0.0565674794
## PctVacMore6Mos -0.0610537739 -0.0617871477 -0.0621147894 -0.0628111932
## MedYrHousBuilt -0.0116043130 -0.0119566691 -0.0123062708 -0.0125654713
## PctHousNoPhone 0.0239859947 0.0241078981 0.0244387787 0.0244453377
## PctWOFullPlumb -0.0092493310 -0.0095367110 -0.0097244028 -0.0100683690
## OwnOccLowQuart -0.1367909929 -0.1451101406 -0.1467820025 -0.1552260441
## OwnOccMedVal . . 0.0002422739 0.0043102967
## OwnOccHiQuart 0.0495828042 0.0568243744 0.0577851235 0.0624268896
## RentLowQ -0.2145440093 -0.2163946431 -0.2169277229 -0.2189846329
## RentMedian . . . .
## RentHighQ -0.0003110822 -0.0030152120 -0.0037044754 -0.0083485662
## MedRent 0.2447747466 0.2500910378 0.2514091699 0.2580513637
## MedRentPctHousInc 0.0451715803 0.0452327270 0.0455113721 0.0456984965
## MedOwnCostPctInc -0.0364967979 -0.0369748582 -0.0371783638 -0.0380154868
## MedOwnCostPctIncNoMtg -0.0753465948 -0.0755852523 -0.0759289107 -0.0758422433
## NumInShelters 0.1092813298 0.1109230447 0.1113877005 0.1135167730
## NumStreet 0.1839087381 0.1839603973 0.1843936054 0.1844572422
## PctForeignBorn 0.0720288893 0.0744713635 0.0747305533 0.0760493662
## PctBornSameState . . . .
## PctSameHouse85 . . . .
## PctSameCity85 0.0243576758 0.0242242259 0.0240121111 0.0237572312
## PctSameState85 0.0127285491 0.0132454851 0.0136413922 0.0140726679
## LandArea 0.0171697699 0.0177062112 0.0181201278 0.0185924522
## PopDens -0.0028745511 -0.0030778597 -0.0033552978 -0.0036165577
## PctUsePubTrans -0.0338375417 -0.0345258918 -0.0346947009 -0.0354737568
##
## (Intercept) 6.337369e-01 6.375051e-01 0.6412110752 6.433449e-01
## (Intercept) . . . .
## state -7.593085e-04 -7.547520e-04 -0.0007519739 -7.512948e-04
## fold -1.714645e-03 -1.709529e-03 -0.0017066327 -1.704793e-03
## population . . . .
## householdsize . . . .
## racepctblack 2.051879e-01 2.056062e-01 0.2059546082 2.060496e-01
## racePctWhite -3.301702e-02 -3.323765e-02 -0.0335155658 -3.391444e-02
## racePctAsian -5.804700e-03 -6.547120e-03 -0.0067075288 -7.138295e-03
## racePctHisp 5.019796e-02 5.149375e-02 0.0527761987 5.298069e-02
## agePct12t21 4.987462e-02 4.943221e-02 0.0488182587 4.805493e-02
## agePct12t29 -2.924619e-01 -2.953916e-01 -0.2977925447 -2.995587e-01
## agePct16t24 . . . -1.243071e-05
## agePct65up 2.426943e-02 2.571127e-02 0.0253536135 2.539154e-02
## numbUrban -7.485739e-02 -7.910050e-02 -0.0826259638 -8.456237e-02
## pctUrban 4.302490e-02 4.317045e-02 0.0433348939 4.336831e-02
## medIncome . . -0.0006755290 -4.436478e-03
## pctWWage -1.829021e-01 -1.871606e-01 -0.1913528517 -1.925304e-01
## pctWFarmSelf 4.222391e-02 4.282772e-02 0.0432493011 4.363341e-02
## pctWInvInc -1.458197e-01 -1.475628e-01 -0.1488300924 -1.493832e-01
## pctWSocSec 5.331205e-02 5.280586e-02 0.0540140575 5.506811e-02
## pctWPubAsst -1.589657e-03 -1.609757e-03 -0.0024515727 -2.626181e-03
## pctWRetire -8.562873e-02 -8.543700e-02 -0.0855415603 -8.565462e-02
## medFamInc 1.190924e-01 1.262867e-01 0.1329135491 1.382258e-01
## perCapInc . 1.100181e-04 0.0021214081 3.488980e-03
## whitePerCap -2.236136e-01 -2.318057e-01 -0.2406761597 -2.456362e-01
## blackPerCap -2.871316e-02 -2.912858e-02 -0.0295090315 -2.969308e-02
## indianPerCap -3.023945e-02 -3.052695e-02 -0.0307465278 -3.083547e-02
## AsianPerCap 2.304534e-02 2.283518e-02 0.0226537583 2.259262e-02
## OtherPerCap 4.465730e-02 4.475089e-02 0.0448403170 4.491791e-02
## HispPerCap 2.786643e-02 2.793191e-02 0.0280227721 2.810545e-02
## NumUnderPov 6.083116e-02 6.950652e-02 0.0759609983 7.975543e-02
## PctPopUnderPov -1.632569e-01 -1.643881e-01 -0.1646155856 -1.652316e-01
## PctLess9thGrade -9.433590e-02 -9.817891e-02 -0.0999470535 -1.014103e-01
## PctNotHSGrad 4.371720e-02 4.879091e-02 0.0505399860 5.263571e-02
## PctBSorMore 6.549653e-02 6.796524e-02 0.0677066072 6.880872e-02
## PctUnemployed -7.324282e-03 -6.547900e-03 -0.0056591814 -4.835524e-03
## PctEmploy 2.059523e-01 2.112949e-01 0.2165054508 2.193584e-01
## PctEmplManu -5.300550e-02 -5.400271e-02 -0.0552174835 -5.568426e-02
## PctEmplProfServ -1.132101e-02 -1.281416e-02 -0.0140914613 -1.506904e-02
## PctOccupManu 6.417984e-02 6.548855e-02 0.0675012292 6.798299e-02
## PctOccupMgmtProf 5.778440e-02 6.095105e-02 0.0656791504 6.754868e-02
## MalePctDivorce 1.874566e-01 1.893327e-01 0.1920511720 1.945215e-01
## MalePctNevMarr 1.864792e-01 1.894503e-01 0.1919624588 1.937753e-01
## FemalePctDiv -1.564725e-01 -1.583872e-01 -0.1586552855 -1.580912e-01
## TotalPctDiv -7.689204e-05 -1.853254e-03 -0.0058203985 -9.645130e-03
## PersPerFam -6.214724e-03 -1.015251e-02 -0.0153370600 -2.077453e-02
## PctFam2Par . . . .
## PctKids2Par -2.773704e-01 -2.793664e-01 -0.2821413451 -2.827081e-01
## PctYoungKids2Par -3.231920e-02 -3.229255e-02 -0.0318843503 -3.201485e-02
## PctTeen2Par -5.276104e-03 -5.727498e-03 -0.0058449703 -6.412245e-03
## PctWorkMomYoungKids 4.092143e-02 4.204442e-02 0.0427347135 4.387266e-02
## PctWorkMom -1.745202e-01 -1.758042e-01 -0.1767239158 -1.781206e-01
## NumIlleg -1.134876e-01 -1.186304e-01 -0.1219289807 -1.250156e-01
## PctIlleg 1.290445e-01 1.275580e-01 0.1263375821 1.256202e-01
## NumImmig -1.205373e-01 -1.219829e-01 -0.1233340965 -1.240902e-01
## PctImmigRecent 1.629879e-02 1.828270e-02 0.0198117417 2.092148e-02
## PctImmigRec5 -8.237271e-03 -8.737599e-03 -0.0087899688 -9.073879e-03
## PctImmigRec8 -8.185966e-03 -1.047567e-02 -0.0123455541 -1.354140e-02
## PctImmigRec10 8.269724e-06 1.579240e-03 0.0026210902 3.660242e-03
## PctRecentImmig -2.431181e-02 -3.011914e-02 -0.0346105169 -3.776982e-02
## PctRecImmig5 . -1.806593e-05 -0.0002404767 -6.703422e-04
## PctRecImmig8 5.392462e-02 6.081313e-02 0.0664228291 6.962971e-02
## PctRecImmig10 . . . .
## PctSpeakEnglOnly -2.137423e-02 -2.353598e-02 -0.0251633321 -2.614371e-02
## PctNotSpeakEnglWell -1.041574e-01 -1.101182e-01 -0.1148376889 -1.181197e-01
## PctLargHouseFam -7.206084e-02 -7.173197e-02 -0.0680578064 -6.560698e-02
## PctLargHouseOccup -5.139653e-02 -5.389709e-02 -0.0589833092 -6.262877e-02
## PersPerOccupHous 4.109163e-01 4.275774e-01 0.4446841387 4.568942e-01
## PersPerOwnOccHous -1.657407e-01 -1.717967e-01 -0.1772284783 -1.795500e-01
## PersPerRentOccHous -1.086687e-01 -1.140552e-01 -0.1198305564 -1.234752e-01
## PctPersOwnOccup -1.355217e-01 -1.402396e-01 -0.1459935428 -1.508629e-01
## PctPersDenseHous 1.822144e-01 1.850003e-01 0.1867009906 1.889711e-01
## PctHousLess3BR 6.847543e-02 7.073379e-02 0.0726134016 7.343892e-02
## MedNumBR 1.638261e-02 1.709856e-02 0.0177175220 1.813372e-02
## HousVacant 1.640983e-01 1.637814e-01 0.1637179825 1.639898e-01
## PctHousOccup -5.271444e-02 -5.247025e-02 -0.0522059108 -5.203791e-02
## PctHousOwnOcc 1.971457e-05 2.107619e-03 0.0054737244 8.626714e-03
## PctVacantBoarded 5.685726e-02 5.715664e-02 0.0573575548 5.752851e-02
## PctVacMore6Mos -6.322005e-02 -6.382018e-02 -0.0644271839 -6.482102e-02
## MedYrHousBuilt -1.301999e-02 -1.340668e-02 -0.0137186953 -1.420625e-02
## PctHousNoPhone 2.421645e-02 2.366848e-02 0.0232872252 2.289342e-02
## PctWOFullPlumb -1.045307e-02 -1.079476e-02 -0.0110567532 -1.131326e-02
## OwnOccLowQuart -1.625690e-01 -1.717060e-01 -0.1812097628 -1.879260e-01
## OwnOccMedVal 8.362070e-03 1.348703e-02 0.0182812234 2.141435e-02
## OwnOccHiQuart 6.536855e-02 6.962135e-02 0.0742684039 7.732317e-02
## RentLowQ -2.194515e-01 -2.207602e-01 -0.2227353607 -2.238269e-01
## RentMedian . . . .
## RentHighQ -1.308672e-02 -1.994120e-02 -0.0261650181 -2.972208e-02
## MedRent 2.628651e-01 2.699731e-01 0.2775095786 2.824764e-01
## MedRentPctHousInc 4.590865e-02 4.597354e-02 0.0459472598 4.585582e-02
## MedOwnCostPctInc -3.845785e-02 -3.900821e-02 -0.0393428493 -3.954465e-02
## MedOwnCostPctIncNoMtg -7.613523e-02 -7.612078e-02 -0.0761626666 -7.626839e-02
## NumInShelters 1.152085e-01 1.169768e-01 0.1183639670 1.196441e-01
## NumStreet 1.847181e-01 1.847378e-01 0.1845117670 1.844406e-01
## PctForeignBorn 7.687521e-02 7.782534e-02 0.0787112410 8.015343e-02
## PctBornSameState . . 0.0001057004 1.358908e-04
## PctSameHouse85 . . . .
## PctSameCity85 2.325871e-02 2.305595e-02 0.0227755808 2.249099e-02
## PctSameState85 1.451187e-02 1.471921e-02 0.0149551403 1.535050e-02
## LandArea 1.921605e-02 1.990020e-02 0.0204896864 2.080440e-02
## PopDens -3.733786e-03 -3.734927e-03 -0.0037057168 -3.887051e-03
## PctUsePubTrans -3.584148e-02 -3.639642e-02 -0.0368524405 -3.702668e-02
##
## (Intercept) 0.6439585039 0.6426140916 0.6423606301 0.6429281231
## (Intercept) . . . .
## state -0.0007497310 -0.0007483362 -0.0007480608 -0.0007479233
## fold -0.0017020464 -0.0016976368 -0.0016953125 -0.0016946590
## population . . . .
## householdsize . . . .
## racepctblack 0.2060866309 0.2062172506 0.2063231387 0.2062617077
## racePctWhite -0.0344663366 -0.0348633977 -0.0353247687 -0.0359000176
## racePctAsian -0.0074368256 -0.0072634462 -0.0070853232 -0.0071024570
## racePctHisp 0.0536673056 0.0551771438 0.0559803037 0.0561067630
## agePct12t21 0.0491940948 0.0532217244 0.0567605824 0.0590560207
## agePct12t29 -0.2989971198 -0.2971941944 -0.2951388281 -0.2934211027
## agePct16t24 -0.0037444244 -0.0113497229 -0.0181558206 -0.0229648376
## agePct65up 0.0260583721 0.0263636585 0.0257823589 0.0253348348
## numbUrban -0.0869926716 -0.0898645962 -0.0915495658 -0.0927423119
## pctUrban 0.0434915788 0.0436995047 0.0437992182 0.0438429215
## medIncome -0.0111483651 -0.0229626345 -0.0345655352 -0.0433848879
## pctWWage -0.1940869097 -0.1963081687 -0.1977177891 -0.1985218797
## pctWFarmSelf 0.0439994359 0.0443370231 0.0445932967 0.0447962672
## pctWInvInc -0.1495017577 -0.1492390673 -0.1491535096 -0.1492895100
## pctWSocSec 0.0556896652 0.0566470422 0.0582614928 0.0595206269
## pctWPubAsst -0.0027144402 -0.0031925067 -0.0037564152 -0.0041386451
## pctWRetire -0.0857110621 -0.0855876819 -0.0856587560 -0.0858034565
## medFamInc 0.1456174599 0.1567766105 0.1662883889 0.1729483446
## perCapInc 0.0045361971 0.0066596596 0.0098568372 0.0126325351
## whitePerCap -0.2508718404 -0.2573394073 -0.2625682830 -0.2662520532
## blackPerCap -0.0298509412 -0.0300610406 -0.0301962006 -0.0303053999
## indianPerCap -0.0309499101 -0.0310946988 -0.0311641611 -0.0312034078
## AsianPerCap 0.0225203052 0.0223832589 0.0222866241 0.0222235702
## OtherPerCap 0.0449631195 0.0449694720 0.0449889194 0.0450258583
## HispPerCap 0.0282087428 0.0283512696 0.0285336131 0.0286691188
## NumUnderPov 0.0843300176 0.0895955133 0.0933486321 0.0961148710
## PctPopUnderPov -0.1665135901 -0.1679199782 -0.1690165017 -0.1700098993
## PctLess9thGrade -0.1029581664 -0.1036664422 -0.1036183845 -0.1038330409
## PctNotHSGrad 0.0546599159 0.0554194270 0.0549646526 0.0549120508
## PctBSorMore 0.0701387752 0.0697443674 0.0684348755 0.0678942038
## PctUnemployed -0.0041102275 -0.0032104084 -0.0024414849 -0.0019230059
## PctEmploy 0.2226724384 0.2270992280 0.2304145182 0.2326436192
## PctEmplManu -0.0563481931 -0.0572606461 -0.0579355385 -0.0583238973
## PctEmplProfServ -0.0160058423 -0.0166872432 -0.0171595682 -0.0174910983
## PctOccupManu 0.0687031715 0.0701506062 0.0712228640 0.0717419502
## PctOccupMgmtProf 0.0694504934 0.0729468229 0.0762213747 0.0782396597
## MalePctDivorce 0.1979303259 0.2037481285 0.2094541766 0.2140508576
## MalePctNevMarr 0.1961337610 0.1992210402 0.2014794318 0.2030105216
## FemalePctDiv -0.1568850255 -0.1539023701 -0.1501550862 -0.1470796217
## TotalPctDiv -0.0149847291 -0.0241079712 -0.0338023030 -0.0416601826
## PersPerFam -0.0266199495 -0.0348018510 -0.0441540214 -0.0520522290
## PctFam2Par . . . .
## PctKids2Par -0.2836773235 -0.2856707243 -0.2874047559 -0.2885077088
## PctYoungKids2Par -0.0321686783 -0.0319355582 -0.0318822354 -0.0320102027
## PctTeen2Par -0.0067653194 -0.0068320073 -0.0068061836 -0.0068263618
## PctWorkMomYoungKids 0.0447303987 0.0453286467 0.0458586942 0.0464181538
## PctWorkMom -0.1793969686 -0.1805868288 -0.1816497557 -0.1826148975
## NumIlleg -0.1277414597 -0.1299894150 -0.1319100641 -0.1337893395
## PctIlleg 0.1248944824 0.1241519281 0.1236126198 0.1232254876
## NumImmig -0.1248087293 -0.1257254079 -0.1265281215 -0.1271209568
## PctImmigRecent 0.0219028930 0.0229409293 0.0236492926 0.0242170744
## PctImmigRec5 -0.0087409890 -0.0082217343 -0.0078465308 -0.0075450351
## PctImmigRec8 -0.0149894732 -0.0165093797 -0.0176843499 -0.0187095199
## PctImmigRec10 0.0045380554 0.0053715040 0.0061898363 0.0068996785
## PctRecentImmig -0.0409450221 -0.0438918338 -0.0455534817 -0.0467582211
## PctRecImmig5 -0.0017949790 -0.0045495574 -0.0081281771 -0.0113577045
## PctRecImmig8 0.0731975599 0.0781980671 0.0828825625 0.0868047177
## PctRecImmig10 . . . .
## PctSpeakEnglOnly -0.0267318477 -0.0268103591 -0.0268825481 -0.0271382363
## PctNotSpeakEnglWell -0.1213915087 -0.1245176463 -0.1260212460 -0.1268322876
## PctLargHouseFam -0.0626028084 -0.0562599146 -0.0486943987 -0.0430409769
## PctLargHouseOccup -0.0671378666 -0.0749402606 -0.0828666680 -0.0886835088
## PersPerOccupHous 0.4703819804 0.4889110940 0.5058046820 0.5181712152
## PersPerOwnOccHous -0.1819741853 -0.1851498587 -0.1870524458 -0.1876810550
## PersPerRentOccHous -0.1277862367 -0.1342748150 -0.1399662095 -0.1439407533
## PctPersOwnOccup -0.1571405884 -0.1669267547 -0.1764514657 -0.1839081017
## PctPersDenseHous 0.1908188617 0.1916129134 0.1917546503 0.1922095324
## PctHousLess3BR 0.0743945700 0.0753599984 0.0761338031 0.0766845923
## MedNumBR 0.0185782008 0.0190039218 0.0193358222 0.0196242523
## HousVacant 0.1640400434 0.1639850441 0.1639736384 0.1641505352
## PctHousOccup -0.0518367506 -0.0516606766 -0.0514928494 -0.0513274170
## PctHousOwnOcc 0.0137283836 0.0225505843 0.0311804737 0.0380388037
## PctVacantBoarded 0.0576731297 0.0577537518 0.0577275241 0.0577237555
## PctVacMore6Mos -0.0652554084 -0.0658134531 -0.0662496433 -0.0665898193
## MedYrHousBuilt -0.0146125963 -0.0148364678 -0.0151298576 -0.0154863746
## PctHousNoPhone 0.0230060537 0.0234935756 0.0237489745 0.0238941847
## PctWOFullPlumb -0.0115247599 -0.0117134619 -0.0118998628 -0.0120411074
## OwnOccLowQuart -0.1950086165 -0.2041602475 -0.2122619567 -0.2182488911
## OwnOccMedVal 0.0254667807 0.0316413870 0.0378546542 0.0430814200
## OwnOccHiQuart 0.0802674680 0.0832326493 0.0846599500 0.0850248033
## RentLowQ -0.2248960210 -0.2264059810 -0.2278766740 -0.2289320035
## RentMedian . . . .
## RentHighQ -0.0334759855 -0.0378194427 -0.0406555774 -0.0423197975
## MedRent 0.2878955401 0.2952091145 0.3012355309 0.3052389445
## MedRentPctHousInc 0.0457448336 0.0453998959 0.0451044558 0.0449379104
## MedOwnCostPctInc -0.0398491343 -0.0400306432 -0.0401482093 -0.0402906017
## MedOwnCostPctIncNoMtg -0.0762628560 -0.0761606720 -0.0761248508 -0.0760700065
## NumInShelters 0.1206266024 0.1213516819 0.1218873946 0.1224158230
## NumStreet 0.1843333515 0.1839710527 0.1836312011 0.1834456782
## PctForeignBorn 0.0823422552 0.0850161673 0.0866489777 0.0875976550
## PctBornSameState 0.0004194918 0.0012785559 0.0019606451 0.0023482671
## PctSameHouse85 . . . .
## PctSameCity85 0.0222275088 0.0219919152 0.0217503306 0.0215291714
## PctSameState85 0.0154819880 0.0150756857 0.0148968416 0.0149556310
## LandArea 0.0211053997 0.0213975010 0.0215403485 0.0215990175
## PopDens -0.0040723158 -0.0040986980 -0.0042775344 -0.0045173256
## PctUsePubTrans -0.0373038275 -0.0375778394 -0.0376896405 -0.0377591897
##
## (Intercept) 0.6431619678 0.6437510032 6.441303e-01 6.441439e-01
## (Intercept) . . . .
## state -0.0007484138 -0.0007495898 -7.505425e-04 -7.511411e-04
## fold -0.0016933005 -0.0016926646 -1.692252e-03 -1.691224e-03
## population . . . .
## householdsize . . . .
## racepctblack 0.2064716771 0.2067618176 2.069468e-01 2.070684e-01
## racePctWhite -0.0364062029 -0.0369501425 -3.752941e-02 -3.818064e-02
## racePctAsian -0.0069341451 -0.0067526378 -6.697031e-03 -6.754903e-03
## racePctHisp 0.0566593898 0.0571397612 5.740287e-02 5.739789e-02
## agePct12t21 0.0622126408 0.0649795783 6.720808e-02 6.959582e-02
## agePct12t29 -0.2922777602 -0.2914778135 -2.904494e-01 -2.886913e-01
## agePct16t24 -0.0284113771 -0.0332135625 -3.745013e-02 -4.227114e-02
## agePct65up 0.0242772318 0.0225890648 2.129886e-02 2.053856e-02
## numbUrban -0.0941519216 -0.0953914267 -9.651889e-02 -9.763383e-02
## pctUrban 0.0439096107 0.0439574440 4.399306e-02 4.401637e-02
## medIncome -0.0528916566 -0.0614531813 -6.864235e-02 -7.652969e-02
## pctWWage -0.1995333632 -0.2001186552 -2.004341e-01 -2.008633e-01
## pctWFarmSelf 0.0449651179 0.0450751598 4.517958e-02 4.530967e-02
## pctWInvInc -0.1493168098 -0.1494223158 -1.495957e-01 -1.497703e-01
## pctWSocSec 0.0612085270 0.0634432861 6.539338e-02 6.713604e-02
## pctWPubAsst -0.0046288372 -0.0050764502 -5.374260e-03 -5.599957e-03
## pctWRetire -0.0859170804 -0.0860662390 -8.617242e-02 -8.623887e-02
## medFamInc 0.1801036484 0.1864533120 1.918797e-01 1.978299e-01
## perCapInc 0.0167517149 0.0219604883 2.694720e-02 3.223201e-02
## whitePerCap -0.2712725452 -0.2767381475 -2.818640e-01 -2.871392e-01
## blackPerCap -0.0304806773 -0.0306588814 -3.082806e-02 -3.100683e-02
## indianPerCap -0.0312441107 -0.0312616962 -3.127996e-02 -3.130257e-02
## AsianPerCap 0.0221395728 0.0220364758 2.194043e-02 2.184087e-02
## OtherPerCap 0.0450595075 0.0451057342 4.515886e-02 4.520917e-02
## HispPerCap 0.0288470635 0.0290051555 2.911580e-02 2.919939e-02
## NumUnderPov 0.0993315776 0.1019967441 1.040515e-01 1.061063e-01
## PctPopUnderPov -0.1709790722 -0.1717014593 -1.722744e-01 -1.728436e-01
## PctLess9thGrade -0.1037902531 -0.1034873568 -1.033310e-01 -1.034319e-01
## PctNotHSGrad 0.0544567369 0.0537129816 5.324332e-02 5.313367e-02
## PctBSorMore 0.0668071979 0.0653623365 6.439885e-02 6.378410e-02
## PctUnemployed -0.0014181114 -0.0009617028 -5.962313e-04 -1.935730e-04
## PctEmploy 0.2351748695 0.2372759280 2.390306e-01 2.410012e-01
## PctEmplManu -0.0589329924 -0.0594819027 -5.989156e-02 -6.021244e-02
## PctEmplProfServ -0.0178742928 -0.0182695991 -1.861610e-02 -1.895135e-02
## PctOccupManu 0.0725858083 0.0732737470 7.368771e-02 7.389381e-02
## PctOccupMgmtProf 0.0809306175 0.0836426639 8.573976e-02 8.755518e-02
## MalePctDivorce 0.2195678028 0.2251049398 2.303338e-01 2.364768e-01
## MalePctNevMarr 0.2048294833 0.2064292210 2.077971e-01 2.092106e-01
## FemalePctDiv -0.1430657289 -0.1386075522 -1.342366e-01 -1.288077e-01
## TotalPctDiv -0.0512488697 -0.0613658449 -7.099067e-02 -8.229433e-02
## PersPerFam -0.0604763384 -0.0689606669 -7.656628e-02 -8.460587e-02
## PctFam2Par . . . .
## PctKids2Par -0.2898414928 -0.2909535624 -2.918290e-01 -2.926854e-01
## PctYoungKids2Par -0.0320367322 -0.0320436495 -3.208564e-02 -3.213197e-02
## PctTeen2Par -0.0067094941 -0.0066126937 -6.548104e-03 -6.467638e-03
## PctWorkMomYoungKids 0.0466834228 0.0469491131 4.721366e-02 4.751836e-02
## PctWorkMom -0.1833239966 -0.1838949760 -1.843963e-01 -1.849411e-01
## NumIlleg -0.1353588889 -0.1366722832 -1.377698e-01 -1.389271e-01
## PctIlleg 0.1228054787 0.1223360084 1.219163e-01 1.215175e-01
## NumImmig -0.1277205149 -0.1282159857 -1.286068e-01 -1.289798e-01
## PctImmigRecent 0.0247005557 0.0251144635 2.548354e-02 2.580330e-02
## PctImmigRec5 -0.0070538743 -0.0064163002 -5.674136e-03 -4.697010e-03
## PctImmigRec8 -0.0198256406 -0.0210434326 -2.224962e-02 -2.351968e-02
## PctImmigRec10 0.0075652843 0.0081888257 8.706427e-03 9.149377e-03
## PctRecentImmig -0.0477618046 -0.0485217706 -4.915024e-02 -4.953759e-02
## PctRecImmig5 -0.0158764009 -0.0212221290 -2.665056e-02 -3.311984e-02
## PctRecImmig8 0.0921885118 0.0984274285 1.045565e-01 1.116331e-01
## PctRecImmig10 . . -9.853331e-06 -2.635694e-04
## PctSpeakEnglOnly -0.0272261948 -0.0273227600 -2.754541e-02 -2.820264e-02
## PctNotSpeakEnglWell -0.1272348128 -0.1274302602 -1.277437e-01 -1.282593e-01
## PctLargHouseFam -0.0362813493 -0.0292810804 -2.328129e-02 -1.710110e-02
## PctLargHouseOccup -0.0950303804 -0.1011352178 -1.064527e-01 -1.122858e-01
## PersPerOccupHous 0.5309952567 0.5424667449 5.520347e-01 5.620922e-01
## PersPerOwnOccHous -0.1882303084 -0.1881683154 -1.875350e-01 -1.863141e-01
## PersPerRentOccHous -0.1481542044 -0.1519464955 -1.551872e-01 -1.587484e-01
## PctPersOwnOccup -0.1928242564 -0.2022545993 -2.113657e-01 -2.220139e-01
## PctPersDenseHous 0.1914758425 0.1904545255 1.898853e-01 1.898021e-01
## PctHousLess3BR 0.0774895055 0.0783161114 7.905601e-02 7.976322e-02
## MedNumBR 0.0199049390 0.0201778753 2.044303e-02 2.072671e-02
## HousVacant 0.1641881374 0.1644054353 1.647507e-01 1.651033e-01
## PctHousOccup -0.0511587067 -0.0509606031 -5.073512e-02 -5.044649e-02
## PctHousOwnOcc 0.0462729508 0.0548539776 6.332474e-02 7.353580e-02
## PctVacantBoarded 0.0576301349 0.0575244422 5.743889e-02 5.732549e-02
## PctVacMore6Mos -0.0669517272 -0.0673004503 -6.760631e-02 -6.789337e-02
## MedYrHousBuilt -0.0157358951 -0.0160375200 -1.635192e-02 -1.668233e-02
## PctHousNoPhone 0.0240982558 0.0242128327 2.427394e-02 2.426369e-02
## PctWOFullPlumb -0.0121954156 -0.0123321243 -1.245596e-02 -1.258925e-02
## OwnOccLowQuart -0.2253420511 -0.2332674440 -2.408792e-01 -2.491505e-01
## OwnOccMedVal 0.0500766820 0.0580901484 6.595726e-02 7.487016e-02
## OwnOccHiQuart 0.0846558111 0.0838894725 8.299829e-02 8.168822e-02
## RentLowQ -0.2300776582 -0.2311399909 -2.320028e-01 -2.327774e-01
## RentMedian . . . .
## RentHighQ -0.0437433112 -0.0449600112 -4.612626e-02 -4.744718e-02
## MedRent 0.3091902233 0.3126896802 3.156187e-01 3.186232e-01
## MedRentPctHousInc 0.0447505324 0.0446432926 4.458196e-02 4.448750e-02
## MedOwnCostPctInc -0.0404406633 -0.0405386913 -4.060207e-02 -4.064926e-02
## MedOwnCostPctIncNoMtg -0.0760074780 -0.0759484294 -7.587687e-02 -7.577764e-02
## NumInShelters 0.1227853741 0.1231879187 1.236665e-01 1.241919e-01
## NumStreet 0.1831026377 0.1826949419 1.823310e-01 1.819602e-01
## PctForeignBorn 0.0882516458 0.0884269629 8.858944e-02 8.866644e-02
## PctBornSameState 0.0030141577 0.0035768578 4.062487e-03 4.589697e-03
## PctSameHouse85 . . . -3.387379e-05
## PctSameCity85 0.0213811254 0.0212682267 2.118568e-02 2.108748e-02
## PctSameState85 0.0147628132 0.0146639113 1.461218e-02 1.455963e-02
## LandArea 0.0216275294 0.0215865070 2.156494e-02 2.153934e-02
## PopDens -0.0047534506 -0.0050321468 -5.295247e-03 -5.578175e-03
## PctUsePubTrans -0.0378813251 -0.0379857074 -3.806879e-02 -3.811176e-02
##
## (Intercept) 0.6437157723 6.430282e-01 0.6419464266 0.6408235533
## (Intercept) . . . .
## state -0.0007513108 -7.512659e-04 -0.0007511509 -0.0007506671
## fold -0.0016899221 -1.688432e-03 -0.0016866000 -0.0016857428
## population . 3.840233e-05 0.0008094939 0.0022439713
## householdsize . . . -0.0006194785
## racepctblack 0.2071962843 2.072590e-01 0.2072591834 0.2072562973
## racePctWhite -0.0387815959 -3.936243e-02 -0.0399766976 -0.0405526189
## racePctAsian -0.0068525453 -6.971674e-03 -0.0070995973 -0.0071686447
## racePctHisp 0.0573115689 5.719880e-02 0.0570717676 0.0568855591
## agePct12t21 0.0718994265 7.410214e-02 0.0764293787 0.0787108465
## agePct12t29 -0.2865310347 -2.842011e-01 -0.2815498516 -0.2791714511
## agePct16t24 -0.0472023771 -5.194927e-02 -0.0569429271 -0.0615555831
## agePct65up 0.0201570869 2.003983e-02 0.0201103472 0.0201796961
## numbUrban -0.0986275506 -9.952599e-02 -0.1010059820 -0.1029336825
## pctUrban 0.0440327264 4.404487e-02 0.0440786284 0.0441236852
## medIncome -0.0842072457 -9.127694e-02 -0.0984792118 -0.1050694651
## pctWWage -0.2013030086 -2.017032e-01 -0.2020968510 -0.2025111356
## pctWFarmSelf 0.0454475216 4.558172e-02 0.0457159758 0.0458864435
## pctWInvInc -0.1499180215 -1.500608e-01 -0.1501956056 -0.1502254234
## pctWSocSec 0.0685463441 6.961593e-02 0.0705494759 0.0714181573
## pctWPubAsst -0.0057691021 -5.867352e-03 -0.0059451867 -0.0061491203
## pctWRetire -0.0862465067 -8.622742e-02 -0.0862063988 -0.0862238698
## medFamInc 0.2037480052 2.091890e-01 0.2147262117 0.2199484426
## perCapInc 0.0373568028 4.206622e-02 0.0468904943 0.0509601389
## whitePerCap -0.2921616584 -2.966595e-01 -0.3010978634 -0.3047663796
## blackPerCap -0.0311736295 -3.132194e-02 -0.0314771876 -0.0316130046
## indianPerCap -0.0313399777 -3.138318e-02 -0.0314293574 -0.0314793427
## AsianPerCap 0.0217359813 2.163852e-02 0.0215332541 0.0214373548
## OtherPerCap 0.0452426981 4.526749e-02 0.0452861509 0.0453135634
## HispPerCap 0.0292714949 2.933655e-02 0.0293987245 0.0294193118
## NumUnderPov 0.1079821831 1.096335e-01 0.1111817386 0.1124679499
## PctPopUnderPov -0.1732782953 -1.736398e-01 -0.1739645632 -0.1742437838
## PctLess9thGrade -0.1036262584 -1.038500e-01 -0.1040530594 -0.1044597494
## PctNotHSGrad 0.0532132702 5.334081e-02 0.0534620653 0.0536110602
## PctBSorMore 0.0633075589 6.293899e-02 0.0625313673 0.0618697154
## PctUnemployed . . . .
## PctEmploy 0.2427985217 2.442878e-01 0.2457269858 0.2469122966
## PctEmplManu -0.0604596259 -6.065496e-02 -0.0608237292 -0.0609547866
## PctEmplProfServ -0.0192588388 -1.955001e-02 -0.0198197586 -0.0199612351
## PctOccupManu 0.0739793504 7.401712e-02 0.0739999077 0.0739477238
## PctOccupMgmtProf 0.0891166032 9.044680e-02 0.0917384202 0.0929550509
## MalePctDivorce 0.2428204136 2.490087e-01 0.2557100285 0.2621158991
## MalePctNevMarr 0.2105082806 2.116442e-01 0.2127197841 0.2139417161
## FemalePctDiv -0.1228130314 -1.166924e-01 -0.1098261406 -0.1033702221
## TotalPctDiv -0.0942314751 -1.060456e-01 -0.1189985968 -0.1312397980
## PersPerFam -0.0920226203 -9.843935e-02 -0.1046438603 -0.1087911516
## PctFam2Par . . . .
## PctKids2Par -0.2934908913 -2.942372e-01 -0.2950072968 -0.2958165002
## PctYoungKids2Par -0.0321717732 -3.220920e-02 -0.0322173747 -0.0322285759
## PctTeen2Par -0.0063968980 -6.335639e-03 -0.0062758051 -0.0062323800
## PctWorkMomYoungKids 0.0478009904 4.806886e-02 0.0483277923 0.0485934103
## PctWorkMom -0.1854196885 -1.858381e-01 -0.1862158408 -0.1865811919
## NumIlleg -0.1400672698 -1.411031e-01 -0.1420809944 -0.1430287086
## PctIlleg 0.1211636957 1.208466e-01 0.1205424404 0.1203415760
## NumImmig -0.1293597335 -1.297092e-01 -0.1300570607 -0.1302800584
## PctImmigRecent 0.0259798363 2.604755e-02 0.0260496597 0.0259781060
## PctImmigRec5 -0.0036458331 -2.622584e-03 -0.0015173423 -0.0004917267
## PctImmigRec8 -0.0247519514 -2.599087e-02 -0.0273919972 -0.0287143645
## PctImmigRec10 0.0096444916 1.025156e-02 0.0110079961 0.0118036515
## PctRecentImmig -0.0494042854 -4.892213e-02 -0.0482125515 -0.0474537835
## PctRecImmig5 -0.0399121337 -4.641694e-02 -0.0532249495 -0.0593979117
## PctRecImmig8 0.1191800068 1.268310e-01 0.1354560953 0.1436015173
## PctRecImmig10 -0.0018057120 -4.350211e-03 -0.0079924357 -0.0119903412
## PctSpeakEnglOnly -0.0287775671 -2.919985e-02 -0.0294960837 -0.0294715439
## PctNotSpeakEnglWell -0.1287736999 -1.291938e-01 -0.1295296437 -0.1292631982
## PctLargHouseFam -0.0111091940 -5.544514e-03 . .
## PctLargHouseOccup -0.1181738081 -1.238318e-01 -0.1296428962 -0.1301560432
## PersPerOccupHous 0.5716139092 5.800249e-01 0.5881719292 0.5947222787
## PersPerOwnOccHous -0.1847773190 -1.830709e-01 -0.1809987488 -0.1790840062
## PersPerRentOccHous -0.1623866516 -1.658655e-01 -0.1695010153 -0.1729601952
## PctPersOwnOccup -0.2334159572 -2.448419e-01 -0.2574497474 -0.2696117726
## PctPersDenseHous 0.1899572217 1.902066e-01 0.1905107392 0.1910624390
## PctHousLess3BR 0.0804488232 8.107809e-02 0.0816986470 0.0822924405
## MedNumBR 0.0210057442 2.126011e-02 0.0215140411 0.0217597147
## HousVacant 0.1654292234 1.657247e-01 0.1659847735 0.1662061689
## PctHousOccup -0.0501887111 -4.998110e-02 -0.0497830671 -0.0496388375
## PctHousOwnOcc 0.0847248754 9.609352e-02 0.1087333941 0.1209275261
## PctVacantBoarded 0.0572219295 5.712866e-02 0.0570228999 0.0569273628
## PctVacMore6Mos -0.0681297599 -6.834117e-02 -0.0685456276 -0.0687357913
## MedYrHousBuilt -0.0170644292 -1.743054e-02 -0.0177973217 -0.0181552098
## PctHousNoPhone 0.0242137009 2.414432e-02 0.0240471071 0.0239894331
## PctWOFullPlumb -0.0127134424 -1.282979e-02 -0.0129272602 -0.0130122034
## OwnOccLowQuart -0.2571913250 -2.645806e-01 -0.2721749819 -0.2789252728
## OwnOccMedVal 0.0838830901 9.245637e-02 0.1015198251 0.1098004572
## OwnOccHiQuart 0.0800174320 7.813511e-02 0.0758917355 0.0736493650
## RentLowQ -0.2334726793 -2.340957e-01 -0.2346841098 -0.2351755342
## RentMedian . . . .
## RentHighQ -0.0486867707 -4.975566e-02 -0.0507849136 -0.0516104816
## MedRent 0.3213815243 3.238200e-01 0.3261880002 0.3282416082
## MedRentPctHousInc 0.0443692525 4.424922e-02 0.0441206488 0.0439921130
## MedOwnCostPctInc -0.0407234194 -4.077784e-02 -0.0408032868 -0.0407792796
## MedOwnCostPctIncNoMtg -0.0756484082 -7.551485e-02 -0.0753770448 -0.0752639993
## NumInShelters 0.1247449443 1.252330e-01 0.1256753648 0.1261780107
## NumStreet 0.1816385147 1.813664e-01 0.1810945543 0.1809075125
## PctForeignBorn 0.0894527566 9.054603e-02 0.0918547484 0.0930915376
## PctBornSameState 0.0051442315 5.677073e-03 0.0062309039 0.0067051515
## PctSameHouse85 -0.0003966790 -7.350660e-04 -0.0010280482 -0.0014033613
## PctSameCity85 0.0210810688 2.109566e-02 0.0211028529 0.0211223315
## PctSameState85 0.0145248614 1.447564e-02 0.0144083050 0.0143679687
## LandArea 0.0215119363 2.147860e-02 0.0213960065 0.0212337369
## PopDens -0.0058476895 -6.095109e-03 -0.0063428134 -0.0066016837
## PctUsePubTrans -0.0381366395 -3.815726e-02 -0.0381684055 -0.0381300366
##
## (Intercept) 0.640162912 0.6396514312 0.6389222528 6.381134e-01
## (Intercept) . . . .
## state -0.000750186 -0.0007498043 -0.0007493858 -7.490090e-04
## fold -0.001684710 -0.0016835301 -0.0016821701 -1.680547e-03
## population 0.003943528 0.0055890382 0.0075288033 9.756289e-03
## householdsize -0.001598585 -0.0024004081 -0.0031083272 -3.696360e-03
## racepctblack 0.207257428 0.2072702725 0.2072764007 2.072782e-01
## racePctWhite -0.040939585 -0.0412109026 -0.0414788747 -4.172108e-02
## racePctAsian -0.007278138 -0.0073999813 -0.0075081075 -7.609871e-03
## racePctHisp 0.056812280 0.0567332935 0.0566295878 5.656188e-02
## agePct12t21 0.080661970 0.0821738438 0.0837192537 8.522765e-02
## agePct12t29 -0.277207331 -0.2757266863 -0.2743259215 -2.729257e-01
## agePct16t24 -0.065282631 -0.0681422902 -0.0709741556 -7.373906e-02
## agePct65up 0.020246566 0.0203619258 0.0205459836 2.082221e-02
## numbUrban -0.105074680 -0.1071511333 -0.1094927792 -1.120711e-01
## pctUrban 0.044187385 0.0442520544 0.0443296465 4.441764e-02
## medIncome -0.110280480 -0.1143415818 -0.1183541589 -1.222813e-01
## pctWWage -0.202825763 -0.2030188858 -0.2031796399 -2.033276e-01
## pctWFarmSelf 0.046010109 0.0461062864 0.0462046923 4.629149e-02
## pctWInvInc -0.150291314 -0.1503650856 -0.1504148722 -1.504511e-01
## pctWSocSec 0.072116347 0.0726613339 0.0732142014 7.371800e-02
## pctWPubAsst -0.006300486 -0.0063946926 -0.0065098284 -6.623104e-03
## pctWRetire -0.086237229 -0.0862484298 -0.0862640363 -8.629343e-02
## medFamInc 0.224001239 0.2271264132 0.2301724329 2.330812e-01
## perCapInc 0.053996519 0.0562651367 0.0584262100 6.050345e-02
## whitePerCap -0.307597340 -0.3097837678 -0.3118616737 -3.138383e-01
## blackPerCap -0.031712228 -0.0317873812 -0.0318705373 -3.194720e-02
## indianPerCap -0.031528086 -0.0315733823 -0.0316161953 -3.165808e-02
## AsianPerCap 0.021363069 0.0213025924 0.0212429851 2.118462e-02
## OtherPerCap 0.045324178 0.0453244201 0.0453205090 4.530956e-02
## HispPerCap 0.029452067 0.0294919960 0.0295326261 2.958080e-02
## NumUnderPov 0.113490379 0.1144199097 0.1153912377 1.163300e-01
## PctPopUnderPov -0.174573402 -0.1748914090 -0.1752467884 -1.756107e-01
## PctLess9thGrade -0.104747752 -0.1050196971 -0.1053269221 -1.056008e-01
## PctNotHSGrad 0.053819442 0.0540593374 0.0543524493 5.466258e-02
## PctBSorMore 0.061483758 0.0612628675 0.0610684186 6.095129e-02
## PctUnemployed . . 0.0001968996 4.716725e-04
## PctEmploy 0.247788159 0.2484799768 0.2492922443 2.501491e-01
## PctEmplManu -0.061078522 -0.0611854150 -0.0612893601 -6.138780e-02
## PctEmplProfServ -0.020112175 -0.0202385025 -0.0203672612 -2.050627e-02
## PctOccupManu 0.073913187 0.0739230532 0.0739366712 7.394255e-02
## PctOccupMgmtProf 0.093881138 0.0945959767 0.0953109015 9.597693e-02
## MalePctDivorce 0.267435413 0.2717307415 0.2760360841 2.803305e-01
## MalePctNevMarr 0.214903110 0.2156733181 0.2164357182 2.171116e-01
## FemalePctDiv -0.098087847 -0.0938502385 -0.0895681916 -8.522830e-02
## TotalPctDiv -0.141409932 -0.1495906448 -0.1578317275 -1.661156e-01
## PersPerFam -0.111762987 -0.1139455847 -0.1159333667 -1.179689e-01
## PctFam2Par . . . .
## PctKids2Par -0.296486330 -0.2969995991 -0.2975151228 -2.980165e-01
## PctYoungKids2Par -0.032205018 -0.0321783501 -0.0321389620 -3.208653e-02
## PctTeen2Par -0.006165954 -0.0061190926 -0.0060749185 -6.023838e-03
## PctWorkMomYoungKids 0.048789617 0.0489301372 0.0490709605 4.920088e-02
## PctWorkMom -0.186848682 -0.1870575630 -0.1872794023 -1.874880e-01
## NumIlleg -0.143734975 -0.1443705584 -0.1450322457 -1.456480e-01
## PctIlleg 0.120237668 0.1201712269 0.1200909712 1.200118e-01
## NumImmig -0.130439435 -0.1305862466 -0.1307331113 -1.308809e-01
## PctImmigRecent 0.025973312 0.0261432755 0.0263433469 2.655267e-02
## PctImmigRec5 . . . 4.354954e-06
## PctImmigRec8 -0.029655079 -0.0302307587 -0.0308842083 -3.159139e-02
## PctImmigRec10 0.012576658 0.0132461316 0.0139733355 1.472649e-02
## PctRecentImmig -0.046863700 -0.0464487752 -0.0461698143 -4.601301e-02
## PctRecImmig5 -0.064255947 -0.0678635085 -0.0712166599 -7.432714e-02
## PctRecImmig8 0.150636767 0.1563145232 0.1620825440 1.679641e-01
## PctRecImmig10 -0.015685927 -0.0189239951 -0.0224109624 -2.609777e-02
## PctSpeakEnglOnly -0.029543481 -0.0296913849 -0.0298144731 -2.995173e-02
## PctNotSpeakEnglWell -0.129396690 -0.1295982080 -0.1297569531 -1.300421e-01
## PctLargHouseFam . . 0.0001020045 6.801084e-04
## PctLargHouseOccup -0.130363873 -0.1305647249 -0.1309442444 -1.317326e-01
## PersPerOccupHous 0.599671800 0.6034034269 0.6068965248 6.102079e-01
## PersPerOwnOccHous -0.177414759 -0.1760321684 -0.1746680562 -1.732311e-01
## PersPerRentOccHous -0.175806489 -0.1780597103 -0.1803005560 -1.825095e-01
## PctPersOwnOccup -0.279813178 -0.2880312805 -0.2962451019 -3.044748e-01
## PctPersDenseHous 0.191542717 0.1919884676 0.1924682080 1.929416e-01
## PctHousLess3BR 0.082621891 0.0828525295 0.0830715476 8.324754e-02
## MedNumBR 0.021959641 0.0221234794 0.0222811426 2.243054e-02
## HousVacant 0.166345399 0.1664449282 0.1665098162 1.665389e-01
## PctHousOccup -0.049512647 -0.0494289614 -0.0493385784 -4.924736e-02
## PctHousOwnOcc 0.131237396 0.1396180385 0.1480327373 1.564571e-01
## PctVacantBoarded 0.056852469 0.0567921772 0.0567187022 5.664576e-02
## PctVacMore6Mos -0.068891394 -0.0690330416 -0.0691742102 -6.930167e-02
## MedYrHousBuilt -0.018471752 -0.0187279814 -0.0189592069 -1.917471e-02
## PctHousNoPhone 0.023946836 0.0239117401 0.0238813153 2.384646e-02
## PctWOFullPlumb -0.013065217 -0.0131090973 -0.0131541782 -1.319953e-02
## OwnOccLowQuart -0.284261199 -0.2884415448 -0.2925997766 -2.967107e-01
## OwnOccMedVal 0.116533151 0.1218844623 0.1272277917 1.325271e-01
## OwnOccHiQuart 0.071771160 0.0702854296 0.0688040699 6.733189e-02
## RentLowQ -0.235590493 -0.2359382068 -0.2362525543 -2.365243e-01
## RentMedian . . . .
## RentHighQ -0.052212442 -0.0526986413 -0.0532046513 -5.370633e-02
## MedRent 0.329891089 0.3312077116 0.3325147633 3.337731e-01
## MedRentPctHousInc 0.043876574 0.0437907190 0.0437006312 4.360638e-02
## MedOwnCostPctInc -0.040803429 -0.0408614001 -0.0409198995 -4.098247e-02
## MedOwnCostPctIncNoMtg -0.075179674 -0.0751121904 -0.0750635018 -7.501860e-02
## NumInShelters 0.126559187 0.1268824787 0.1271815734 1.274377e-01
## NumStreet 0.180765400 0.1806637014 0.1805559867 1.804432e-01
## PctForeignBorn 0.094134534 0.0949937636 0.0958547660 9.670453e-02
## PctBornSameState 0.007056888 0.0073290288 0.0076033344 7.871984e-03
## PctSameHouse85 -0.001844816 -0.0022640747 -0.0026722194 -3.048682e-03
## PctSameCity85 0.021113062 0.0211104628 0.0210988850 2.107460e-02
## PctSameState85 0.014360966 0.0143733132 0.0143716852 1.437342e-02
## LandArea 0.021133197 0.0210683049 0.0209896008 2.091038e-02
## PopDens -0.006828834 -0.0069998666 -0.0071616428 -7.318297e-03
## PctUsePubTrans -0.038116143 -0.0381086564 -0.0380976529 -3.808695e-02
##
## (Intercept) 6.370785e-01 6.358429e-01
## (Intercept) . .
## state -7.486413e-04 -7.481044e-04
## fold -1.678673e-03 -1.676658e-03
## population 1.249188e-02 1.590759e-02
## householdsize -4.224863e-03 -4.735576e-03
## racepctblack 2.072862e-01 2.073014e-01
## racePctWhite -4.196756e-02 -4.221576e-02
## racePctAsian -7.722032e-03 -7.818397e-03
## racePctHisp 5.653201e-02 5.652526e-02
## agePct12t21 8.693137e-02 8.867248e-02
## agePct12t29 -2.713600e-01 -2.694641e-01
## agePct16t24 -7.673339e-02 -7.998053e-02
## agePct65up 2.117101e-02 2.162784e-02
## numbUrban -1.150228e-01 -1.186102e-01
## pctUrban 4.452219e-02 4.464399e-02
## medIncome -1.264475e-01 -1.310684e-01
## pctWWage -2.034656e-01 -2.036345e-01
## pctWFarmSelf 4.637592e-02 4.646844e-02
## pctWInvInc -1.504805e-01 -1.504945e-01
## pctWSocSec 7.417311e-02 7.455176e-02
## pctWPubAsst -6.690294e-03 -6.743856e-03
## pctWRetire -8.631835e-02 -8.635247e-02
## medFamInc 2.360470e-01 2.392827e-01
## perCapInc 6.266141e-02 6.501509e-02
## whitePerCap -3.158314e-01 -3.178799e-01
## blackPerCap -3.202057e-02 -3.209389e-02
## indianPerCap -3.170259e-02 -3.174974e-02
## AsianPerCap 2.112218e-02 2.106051e-02
## OtherPerCap 4.529362e-02 4.527864e-02
## HispPerCap 2.962860e-02 2.967572e-02
## NumUnderPov 1.171800e-01 1.180332e-01
## PctPopUnderPov -1.759942e-01 -1.763677e-01
## PctLess9thGrade -1.058398e-01 -1.060215e-01
## PctNotHSGrad 5.496988e-02 5.524325e-02
## PctBSorMore 6.087973e-02 6.075375e-02
## PctUnemployed 7.385471e-04 9.857262e-04
## PctEmploy 2.510087e-01 2.518518e-01
## PctEmplManu -6.147324e-02 -6.154035e-02
## PctEmplProfServ -2.067473e-02 -2.083660e-02
## PctOccupManu 7.391981e-02 7.384733e-02
## PctOccupMgmtProf 9.664281e-02 9.734355e-02
## MalePctDivorce 2.849532e-01 2.902039e-01
## MalePctNevMarr 2.177425e-01 2.183262e-01
## FemalePctDiv -8.041956e-02 -7.477760e-02
## TotalPctDiv -1.751232e-01 -1.854876e-01
## PersPerFam -1.201504e-01 -1.226384e-01
## PctFam2Par . .
## PctKids2Par -2.985087e-01 -2.989823e-01
## PctYoungKids2Par -3.202750e-02 -3.197103e-02
## PctTeen2Par -5.952228e-03 -5.902423e-03
## PctWorkMomYoungKids 4.934023e-02 4.949449e-02
## PctWorkMom -1.876947e-01 -1.878912e-01
## NumIlleg -1.462293e-01 -1.467886e-01
## PctIlleg 1.199112e-01 1.198026e-01
## NumImmig -1.310505e-01 -1.312371e-01
## PctImmigRecent 2.684605e-02 2.691308e-02
## PctImmigRec5 9.611477e-05 7.203047e-04
## PctImmigRec8 -3.255311e-02 -3.385749e-02
## PctImmigRec10 1.556075e-02 1.645881e-02
## PctRecentImmig -4.602738e-02 -4.617530e-02
## PctRecImmig5 -7.746231e-02 -8.089490e-02
## PctRecImmig8 1.745130e-01 1.821062e-01
## PctRecImmig10 -3.025767e-02 -3.517662e-02
## PctSpeakEnglOnly -3.004713e-02 -3.013151e-02
## PctNotSpeakEnglWell -1.303647e-01 -1.307373e-01
## PctLargHouseFam 1.779460e-03 3.482042e-03
## PctLargHouseOccup -1.330776e-01 -1.350820e-01
## PersPerOccupHous 6.135559e-01 6.171223e-01
## PersPerOwnOccHous -1.716013e-01 -1.695223e-01
## PersPerRentOccHous -1.848546e-01 -1.874281e-01
## PctPersOwnOccup -3.133836e-01 -3.235568e-01
## PctPersDenseHous 1.934229e-01 1.939231e-01
## PctHousLess3BR 8.341617e-02 8.358244e-02
## MedNumBR 2.257499e-02 2.272677e-02
## HousVacant 1.665456e-01 1.665189e-01
## PctHousOccup -4.915059e-02 -4.905237e-02
## PctHousOwnOcc 1.655963e-01 1.760360e-01
## PctVacantBoarded 5.656822e-02 5.647869e-02
## PctVacMore6Mos -6.942569e-02 -6.953543e-02
## MedYrHousBuilt -1.939269e-02 -1.962627e-02
## PctHousNoPhone 2.381747e-02 2.375352e-02
## PctWOFullPlumb -1.324877e-02 -1.329620e-02
## OwnOccLowQuart -3.011107e-01 -3.060642e-01
## OwnOccMedVal 1.381904e-01 1.445948e-01
## OwnOccHiQuart 6.571340e-02 6.382458e-02
## RentLowQ -2.367745e-01 -2.370258e-01
## RentMedian -9.559029e-06 -1.952605e-05
## RentHighQ -5.413085e-02 -5.452863e-02
## MedRent 3.350526e-01 3.363725e-01
## MedRentPctHousInc 4.348571e-02 4.334516e-02
## MedOwnCostPctInc -4.101505e-02 -4.103653e-02
## MedOwnCostPctIncNoMtg -7.497441e-02 -7.493189e-02
## NumInShelters 1.276634e-01 1.278606e-01
## NumStreet 1.803157e-01 1.801715e-01
## PctForeignBorn 9.760336e-02 9.861857e-02
## PctBornSameState 8.176421e-03 8.470026e-03
## PctSameHouse85 -3.356536e-03 -3.630089e-03
## PctSameCity85 2.104926e-02 2.102069e-02
## PctSameState85 1.434782e-02 1.433711e-02
## LandArea 2.079170e-02 2.065857e-02
## PopDens -7.496714e-03 -7.669628e-03
## PctUsePubTrans -3.806240e-02 -3.803492e-02lasso.mod$lambda## [1] 1.719985e-01 1.567186e-01 1.427961e-01 1.301105e-01 1.185519e-01
## [6] 1.080200e-01 9.842384e-02 8.968014e-02 8.171320e-02 7.445402e-02
## [11] 6.783973e-02 6.181304e-02 5.632174e-02 5.131827e-02 4.675930e-02
## [16] 4.260533e-02 3.882039e-02 3.537169e-02 3.222937e-02 2.936620e-02
## [21] 2.675739e-02 2.438034e-02 2.221445e-02 2.024098e-02 1.844283e-02
## [26] 1.680442e-02 1.531156e-02 1.395132e-02 1.271193e-02 1.158263e-02
## [31] 1.055367e-02 9.616107e-03 8.761839e-03 7.983461e-03 7.274232e-03
## [36] 6.628010e-03 6.039195e-03 5.502690e-03 5.013846e-03 4.568430e-03
## [41] 4.162583e-03 3.792791e-03 3.455850e-03 3.148842e-03 2.869107e-03
## [46] 2.614224e-03 2.381983e-03 2.170374e-03 1.977564e-03 1.801883e-03
## [51] 1.641809e-03 1.495955e-03 1.363058e-03 1.241968e-03 1.131635e-03
## [56] 1.031104e-03 9.395032e-04 8.560404e-04 7.799921e-04 7.106997e-04
## [61] 6.475631e-04 5.900354e-04 5.376183e-04 4.898578e-04 4.463401e-04
## [66] 4.066885e-04 3.705594e-04 3.376400e-04 3.076450e-04 2.803146e-04
## [71] 2.554122e-04 2.327221e-04 2.120477e-04 1.932100e-04 1.760458e-04
## [76] 1.604063e-04 1.461563e-04 1.331722e-04 1.213415e-04 1.105619e-04
## [81] 1.007399e-04 9.179040e-05 8.363599e-05 7.620600e-05 6.943607e-05
## [86] 6.326756e-05 5.764705e-05 5.252584e-05 4.785959e-05 4.360788e-05
## [91] 3.973387e-05 3.620403e-05 3.298776e-05 3.005722e-05 2.738702e-05
## [96] 2.495403e-05 2.273718e-05 2.071727e-05 1.887681e-05 1.719985e-05plot(lasso.mod,"lambda", label=TRUE)
lasso.mod$lambda[5]## [1] 0.1185519log(lasso.mod$lambda[5])## [1] -2.132405coef(lasso.mod)[,5] # Lambda más grande penaliza más tienden a ser los beta más pequeños## (Intercept) (Intercept) state
## 0.2951769 0.0000000 0.0000000
## fold population householdsize
## 0.0000000 0.0000000 0.0000000
## racepctblack racePctWhite racePctAsian
## 0.0000000 0.0000000 0.0000000
## racePctHisp agePct12t21 agePct12t29
## 0.0000000 0.0000000 0.0000000
## agePct16t24 agePct65up numbUrban
## 0.0000000 0.0000000 0.0000000
## pctUrban medIncome pctWWage
## 0.0000000 0.0000000 0.0000000
## pctWFarmSelf pctWInvInc pctWSocSec
## 0.0000000 0.0000000 0.0000000
## pctWPubAsst pctWRetire medFamInc
## 0.0000000 0.0000000 0.0000000
## perCapInc whitePerCap blackPerCap
## 0.0000000 0.0000000 0.0000000
## indianPerCap AsianPerCap OtherPerCap
## 0.0000000 0.0000000 0.0000000
## HispPerCap NumUnderPov PctPopUnderPov
## 0.0000000 0.0000000 0.0000000
## PctLess9thGrade PctNotHSGrad PctBSorMore
## 0.0000000 0.0000000 0.0000000
## PctUnemployed PctEmploy PctEmplManu
## 0.0000000 0.0000000 0.0000000
## PctEmplProfServ PctOccupManu PctOccupMgmtProf
## 0.0000000 0.0000000 0.0000000
## MalePctDivorce MalePctNevMarr FemalePctDiv
## 0.0000000 0.0000000 0.0000000
## TotalPctDiv PersPerFam PctFam2Par
## 0.0000000 0.0000000 0.0000000
## PctKids2Par PctYoungKids2Par PctTeen2Par
## -0.1411978 0.0000000 0.0000000
## PctWorkMomYoungKids PctWorkMom NumIlleg
## 0.0000000 0.0000000 0.0000000
## PctIlleg NumImmig PctImmigRecent
## 0.1217523 0.0000000 0.0000000
## PctImmigRec5 PctImmigRec8 PctImmigRec10
## 0.0000000 0.0000000 0.0000000
## PctRecentImmig PctRecImmig5 PctRecImmig8
## 0.0000000 0.0000000 0.0000000
## PctRecImmig10 PctSpeakEnglOnly PctNotSpeakEnglWell
## 0.0000000 0.0000000 0.0000000
## PctLargHouseFam PctLargHouseOccup PersPerOccupHous
## 0.0000000 0.0000000 0.0000000
## PersPerOwnOccHous PersPerRentOccHous PctPersOwnOccup
## 0.0000000 0.0000000 0.0000000
## PctPersDenseHous PctHousLess3BR MedNumBR
## 0.0000000 0.0000000 0.0000000
## HousVacant PctHousOccup PctHousOwnOcc
## 0.0000000 0.0000000 0.0000000
## PctVacantBoarded PctVacMore6Mos MedYrHousBuilt
## 0.0000000 0.0000000 0.0000000
## PctHousNoPhone PctWOFullPlumb OwnOccLowQuart
## 0.0000000 0.0000000 0.0000000
## OwnOccMedVal OwnOccHiQuart RentLowQ
## 0.0000000 0.0000000 0.0000000
## RentMedian RentHighQ MedRent
## 0.0000000 0.0000000 0.0000000
## MedRentPctHousInc MedOwnCostPctInc MedOwnCostPctIncNoMtg
## 0.0000000 0.0000000 0.0000000
## NumInShelters NumStreet PctForeignBorn
## 0.0000000 0.0000000 0.0000000
## PctBornSameState PctSameHouse85 PctSameCity85
## 0.0000000 0.0000000 0.0000000
## PctSameState85 LandArea PopDens
## 0.0000000 0.0000000 0.0000000
## PctUsePubTrans
## 0.0000000plot(lasso.mod,"lambda", label=TRUE)
abline(v = log(lasso.mod$lambda[5]), col="blue", lwd=4, lty=3)
lasso.mod$lambda[60]## [1] 0.0007106997log(lasso.mod$lambda[60])## [1] -7.249261coef(lasso.mod)[,60] # Lambda más grande penaliza más tienden a ser los beta más pequeños## (Intercept) (Intercept) state
## 5.697581e-01 0.000000e+00 -8.302962e-04
## fold population householdsize
## -1.646556e-03 0.000000e+00 1.004444e-02
## racepctblack racePctWhite racePctAsian
## 1.862461e-01 -2.851002e-02 0.000000e+00
## racePctHisp agePct12t21 agePct12t29
## 1.351425e-02 1.224598e-02 -1.540542e-01
## agePct16t24 agePct65up numbUrban
## 0.000000e+00 0.000000e+00 -1.209772e-03
## pctUrban medIncome pctWWage
## 3.575345e-02 0.000000e+00 -8.632610e-02
## pctWFarmSelf pctWInvInc pctWSocSec
## 2.143952e-02 -8.475446e-02 1.407931e-02
## pctWPubAsst pctWRetire medFamInc
## 0.000000e+00 -7.184448e-02 0.000000e+00
## perCapInc whitePerCap blackPerCap
## 0.000000e+00 -5.262569e-02 -1.843241e-02
## indianPerCap AsianPerCap OtherPerCap
## -2.495286e-02 2.177364e-02 3.941744e-02
## HispPerCap NumUnderPov PctPopUnderPov
## 1.759589e-02 0.000000e+00 -1.095520e-01
## PctLess9thGrade PctNotHSGrad PctBSorMore
## -2.827185e-02 0.000000e+00 0.000000e+00
## PctUnemployed PctEmploy PctEmplManu
## -1.750846e-02 7.310291e-02 -1.836000e-02
## PctEmplProfServ PctOccupManu PctOccupMgmtProf
## 0.000000e+00 1.346640e-03 0.000000e+00
## MalePctDivorce MalePctNevMarr FemalePctDiv
## 1.152398e-01 8.597559e-02 -4.552063e-02
## TotalPctDiv PersPerFam PctFam2Par
## 0.000000e+00 0.000000e+00 0.000000e+00
## PctKids2Par PctYoungKids2Par PctTeen2Par
## -2.338313e-01 -3.680902e-02 0.000000e+00
## PctWorkMomYoungKids PctWorkMom NumIlleg
## 0.000000e+00 -1.093346e-01 -5.009782e-02
## PctIlleg NumImmig PctImmigRecent
## 1.635443e-01 -9.810651e-02 0.000000e+00
## PctImmigRec5 PctImmigRec8 PctImmigRec10
## -1.458470e-03 0.000000e+00 0.000000e+00
## PctRecentImmig PctRecImmig5 PctRecImmig8
## 0.000000e+00 0.000000e+00 0.000000e+00
## PctRecImmig10 PctSpeakEnglOnly PctNotSpeakEnglWell
## 1.348307e-02 0.000000e+00 0.000000e+00
## PctLargHouseFam PctLargHouseOccup PersPerOccupHous
## -4.570750e-03 0.000000e+00 1.220729e-02
## PersPerOwnOccHous PersPerRentOccHous PctPersOwnOccup
## 0.000000e+00 0.000000e+00 -3.577309e-02
## PctPersDenseHous PctHousLess3BR MedNumBR
## 1.185666e-01 1.723298e-02 0.000000e+00
## HousVacant PctHousOccup PctHousOwnOcc
## 1.274867e-01 -5.799251e-02 0.000000e+00
## PctVacantBoarded PctVacMore6Mos MedYrHousBuilt
## 4.812779e-02 -3.859766e-02 -6.629567e-03
## PctHousNoPhone PctWOFullPlumb OwnOccLowQuart
## 1.483078e-02 -4.728094e-05 -2.982638e-02
## OwnOccMedVal OwnOccHiQuart RentLowQ
## 0.000000e+00 0.000000e+00 -1.490333e-01
## RentMedian RentHighQ MedRent
## 0.000000e+00 0.000000e+00 1.440134e-01
## MedRentPctHousInc MedOwnCostPctInc MedOwnCostPctIncNoMtg
## 4.775178e-02 -2.111580e-02 -6.608510e-02
## NumInShelters NumStreet PctForeignBorn
## 6.668756e-02 1.801051e-01 3.182539e-02
## PctBornSameState PctSameHouse85 PctSameCity85
## 0.000000e+00 0.000000e+00 2.180302e-02
## PctSameState85 LandArea PopDens
## 0.000000e+00 0.000000e+00 0.000000e+00
## PctUsePubTrans
## -1.129408e-02plot(lasso.mod,"lambda", label=TRUE)
abline(v = log(lasso.mod$lambda[60]), col="blue", lwd=4, lty=3)
datosx<-model.matrix(ViolentCrimesPerPop~.,datos)[,-c(103)]
pred<-predict(lasso.mod,s=lasso.mod$lambda[5],newx=datosx)
# Medición de precisión
numero.predictoras <- dim(datosx)[2]-1
pre.lasso <- indices.precision(datos$ViolentCrimesPerPop,pred,numero.predictoras)
pre.lasso## $error.cuadratico
## [1] 0.03766304
##
## $raiz.error.cuadratico
## [1] 0.1992323
##
## $error.relativo
## [1] 0.6140855
##
## $correlacion
## [1] 0.7633719pred<-predict(lasso.mod,s=lasso.mod$lambda[60],newx=datosx)
# Medición de precisión
numero.predictoras <- dim(datosx)[2]-1
pre.lasso <- indices.precision(datos$ViolentCrimesPerPop,pred,numero.predictoras)
pre.lasso## $error.cuadratico
## [1] 0.01713597
##
## $raiz.error.cuadratico
## [1] 0.1343867
##
## $error.relativo
## [1] 0.3835721
##
## $correlacion
## [1] 0.8272048# Validación Cruzada
sal.cv<-cv.glmnet(x,y,alpha=1)
plot(sal.cv)
mejor.lambda<-sal.cv$lambda.min
mejor.lambda## [1] 0.00033764log(mejor.lambda)## [1] -7.99353coef(lasso.mod)[,which(lasso.mod$lambda==mejor.lambda)]## (Intercept) (Intercept) state
## 0.5867939833 0.0000000000 -0.0007858794
## fold population householdsize
## -0.0017100313 0.0000000000 0.0109853844
## racepctblack racePctWhite racePctAsian
## 0.1978777359 -0.0279480711 0.0000000000
## racePctHisp agePct12t21 agePct12t29
## 0.0421725769 0.0407171466 -0.2451626702
## agePct16t24 agePct65up numbUrban
## 0.0000000000 0.0141380334 -0.0368177420
## pctUrban medIncome pctWWage
## 0.0400617425 0.0000000000 -0.1487669827
## pctWFarmSelf pctWInvInc pctWSocSec
## 0.0336520363 -0.1267180313 0.0414632333
## pctWPubAsst pctWRetire medFamInc
## 0.0000000000 -0.0814707917 0.0502009501
## perCapInc whitePerCap blackPerCap
## 0.0000000000 -0.1246292766 -0.0239358980
## indianPerCap AsianPerCap OtherPerCap
## -0.0276577806 0.0238124005 0.0426492109
## HispPerCap NumUnderPov PctPopUnderPov
## 0.0249296609 0.0000000000 -0.1403779045
## PctLess9thGrade PctNotHSGrad PctBSorMore
## -0.0531177249 0.0000000000 0.0431119096
## PctUnemployed PctEmploy PctEmplManu
## -0.0123550179 0.1562679486 -0.0366996818
## PctEmplProfServ PctOccupManu PctOccupMgmtProf
## 0.0000000000 0.0366284486 0.0162660525
## MalePctDivorce MalePctNevMarr FemalePctDiv
## 0.1673019144 0.1520612130 -0.1188392063
## TotalPctDiv PersPerFam PctFam2Par
## 0.0000000000 0.0000000000 0.0000000000
## PctKids2Par PctYoungKids2Par PctTeen2Par
## -0.2609602081 -0.0311486612 0.0000000000
## PctWorkMomYoungKids PctWorkMom NumIlleg
## 0.0175615502 -0.1457818573 -0.0727498912
## PctIlleg NumImmig PctImmigRecent
## 0.1454842368 -0.1036392364 0.0018233948
## PctImmigRec5 PctImmigRec8 PctImmigRec10
## -0.0036430717 -0.0004765115 0.0000000000
## PctRecentImmig PctRecImmig5 PctRecImmig8
## 0.0000000000 0.0000000000 0.0203701026
## PctRecImmig10 PctSpeakEnglOnly PctNotSpeakEnglWell
## 0.0000000000 0.0000000000 -0.0564707285
## PctLargHouseFam PctLargHouseOccup PersPerOccupHous
## -0.0632954934 -0.0257936939 0.2207988365
## PersPerOwnOccHous PersPerRentOccHous PctPersOwnOccup
## -0.0750911584 -0.0478297447 -0.0904661539
## PctPersDenseHous PctHousLess3BR MedNumBR
## 0.1583895153 0.0478034348 0.0073570029
## HousVacant PctHousOccup PctHousOwnOcc
## 0.1571483999 -0.0542942644 0.0000000000
## PctVacantBoarded PctVacMore6Mos MedYrHousBuilt
## 0.0533726447 -0.0535339044 -0.0099512256
## PctHousNoPhone PctWOFullPlumb OwnOccLowQuart
## 0.0223358029 -0.0065138077 -0.0721842596
## OwnOccMedVal OwnOccHiQuart RentLowQ
## 0.0000000000 0.0000000000 -0.1974997576
## RentMedian RentHighQ MedRent
## 0.0000000000 0.0000000000 0.2137257248
## MedRentPctHousInc MedOwnCostPctInc MedOwnCostPctIncNoMtg
## 0.0470860508 -0.0316079709 -0.0727961461
## NumInShelters NumStreet PctForeignBorn
## 0.0954364773 0.1831881470 0.0627223555
## PctBornSameState PctSameHouse85 PctSameCity85
## 0.0000000000 0.0000000000 0.0261728386
## PctSameState85 LandArea PopDens
## 0.0067659166 0.0128662561 0.0000000000
## PctUsePubTrans
## -0.0262528417plot(lasso.mod,"lambda", label=TRUE)
abline(v = log(mejor.lambda), col="blue", lwd=4, lty=3)
pred<-predict(lasso.mod,s=mejor.lambda,newx=datosx)
# Medición de precisión
numero.predictoras<- dim(datosx)[2]-1
numero.predictoras## [1] 101pre.lasso <- indices.precision(datos$ViolentCrimesPerPop,pred,numero.predictoras)
pre.lasso## $error.cuadratico
## [1] 0.01676862
##
## $raiz.error.cuadratico
## [1] 0.1329385
##
## $error.relativo
## [1] 0.3807958
##
## $correlacion
## [1] 0.8312561###Elastic Net
# Debemos eliminar la columna 1
x<-model.matrix(ViolentCrimesPerPop~.,datos)[,-c(103)]
head(x)## (Intercept) state fold population householdsize racepctblack racePctWhite
## 1 1 8 1 0.19 0.33 0.02 0.90
## 2 1 53 1 0.00 0.16 0.12 0.74
## 3 1 24 1 0.00 0.42 0.49 0.56
## 4 1 34 1 0.04 0.77 1.00 0.08
## 5 1 42 1 0.01 0.55 0.02 0.95
## 6 1 6 1 0.02 0.28 0.06 0.54
## racePctAsian racePctHisp agePct12t21 agePct12t29 agePct16t24 agePct65up
## 1 0.12 0.17 0.34 0.47 0.29 0.32
## 2 0.45 0.07 0.26 0.59 0.35 0.27
## 3 0.17 0.04 0.39 0.47 0.28 0.32
## 4 0.12 0.10 0.51 0.50 0.34 0.21
## 5 0.09 0.05 0.38 0.38 0.23 0.36
## 6 1.00 0.25 0.31 0.48 0.27 0.37
## numbUrban pctUrban medIncome pctWWage pctWFarmSelf pctWInvInc pctWSocSec
## 1 0.20 1.0 0.37 0.72 0.34 0.60 0.29
## 2 0.02 1.0 0.31 0.72 0.11 0.45 0.25
## 3 0.00 0.0 0.30 0.58 0.19 0.39 0.38
## 4 0.06 1.0 0.58 0.89 0.21 0.43 0.36
## 5 0.02 0.9 0.50 0.72 0.16 0.68 0.44
## 6 0.04 1.0 0.52 0.68 0.20 0.61 0.28
## pctWPubAsst pctWRetire medFamInc perCapInc whitePerCap blackPerCap
## 1 0.15 0.43 0.39 0.40 0.39 0.32
## 2 0.29 0.39 0.29 0.37 0.38 0.33
## 3 0.40 0.84 0.28 0.27 0.29 0.27
## 4 0.20 0.82 0.51 0.36 0.40 0.39
## 5 0.11 0.71 0.46 0.43 0.41 0.28
## 6 0.15 0.25 0.62 0.72 0.76 0.77
## indianPerCap AsianPerCap OtherPerCap HispPerCap NumUnderPov PctPopUnderPov
## 1 0.27 0.27 0.36 0.41 0.08 0.19
## 2 0.16 0.30 0.22 0.35 0.01 0.24
## 3 0.07 0.29 0.28 0.39 0.01 0.27
## 4 0.16 0.25 0.36 0.44 0.01 0.10
## 5 0.00 0.74 0.51 0.48 0.00 0.06
## 6 0.28 0.52 0.48 0.60 0.01 0.12
## PctLess9thGrade PctNotHSGrad PctBSorMore PctUnemployed PctEmploy PctEmplManu
## 1 0.10 0.18 0.48 0.27 0.68 0.23
## 2 0.14 0.24 0.30 0.27 0.73 0.57
## 3 0.27 0.43 0.19 0.36 0.58 0.32
## 4 0.09 0.25 0.31 0.33 0.71 0.36
## 5 0.25 0.30 0.33 0.12 0.65 0.67
## 6 0.13 0.12 0.80 0.10 0.65 0.19
## PctEmplProfServ PctOccupManu PctOccupMgmtProf MalePctDivorce MalePctNevMarr
## 1 0.41 0.25 0.52 0.68 0.40
## 2 0.15 0.42 0.36 1.00 0.63
## 3 0.29 0.49 0.32 0.63 0.41
## 4 0.45 0.37 0.39 0.34 0.45
## 5 0.38 0.42 0.46 0.22 0.27
## 6 0.77 0.06 0.91 0.49 0.57
## FemalePctDiv TotalPctDiv PersPerFam PctFam2Par PctKids2Par PctYoungKids2Par
## 1 0.75 0.75 0.35 0.55 0.59 0.61
## 2 0.91 1.00 0.29 0.43 0.47 0.60
## 3 0.71 0.70 0.45 0.42 0.44 0.43
## 4 0.49 0.44 0.75 0.65 0.54 0.83
## 5 0.20 0.21 0.51 0.91 0.91 0.89
## 6 0.61 0.58 0.44 0.62 0.69 0.87
## PctTeen2Par PctWorkMomYoungKids PctWorkMom NumIlleg PctIlleg NumImmig
## 1 0.56 0.74 0.76 0.04 0.14 0.03
## 2 0.39 0.46 0.53 0.00 0.24 0.01
## 3 0.43 0.71 0.67 0.01 0.46 0.00
## 4 0.65 0.85 0.86 0.03 0.33 0.02
## 5 0.85 0.40 0.60 0.00 0.06 0.00
## 6 0.53 0.30 0.43 0.00 0.11 0.04
## PctImmigRecent PctImmigRec5 PctImmigRec8 PctImmigRec10 PctRecentImmig
## 1 0.24 0.27 0.37 0.39 0.07
## 2 0.52 0.62 0.64 0.63 0.25
## 3 0.07 0.06 0.15 0.19 0.02
## 4 0.11 0.20 0.30 0.31 0.05
## 5 0.03 0.07 0.20 0.27 0.01
## 6 0.30 0.35 0.43 0.47 0.50
## PctRecImmig5 PctRecImmig8 PctRecImmig10 PctSpeakEnglOnly PctNotSpeakEnglWell
## 1 0.07 0.08 0.08 0.89 0.06
## 2 0.27 0.25 0.23 0.84 0.10
## 3 0.02 0.04 0.05 0.88 0.04
## 4 0.08 0.11 0.11 0.81 0.08
## 5 0.02 0.04 0.05 0.88 0.05
## 6 0.50 0.56 0.57 0.45 0.28
## PctLargHouseFam PctLargHouseOccup PersPerOccupHous PersPerOwnOccHous
## 1 0.14 0.13 0.33 0.39
## 2 0.16 0.10 0.17 0.29
## 3 0.20 0.20 0.46 0.52
## 4 0.56 0.62 0.85 0.77
## 5 0.16 0.19 0.59 0.60
## 6 0.25 0.19 0.29 0.53
## PersPerRentOccHous PctPersOwnOccup PctPersDenseHous PctHousLess3BR MedNumBR
## 1 0.28 0.55 0.09 0.51 0.5
## 2 0.17 0.26 0.20 0.82 0.0
## 3 0.43 0.42 0.15 0.51 0.5
## 4 1.00 0.94 0.12 0.01 0.5
## 5 0.37 0.89 0.02 0.19 0.5
## 6 0.18 0.39 0.26 0.73 0.0
## HousVacant PctHousOccup PctHousOwnOcc PctVacantBoarded PctVacMore6Mos
## 1 0.21 0.71 0.52 0.05 0.26
## 2 0.02 0.79 0.24 0.02 0.25
## 3 0.01 0.86 0.41 0.29 0.30
## 4 0.01 0.97 0.96 0.60 0.47
## 5 0.01 0.89 0.87 0.04 0.55
## 6 0.02 0.84 0.30 0.16 0.28
## MedYrHousBuilt PctHousNoPhone PctWOFullPlumb OwnOccLowQuart OwnOccMedVal
## 1 0.65 0.14 0.06 0.22 0.19
## 2 0.65 0.16 0.00 0.21 0.20
## 3 0.52 0.47 0.45 0.18 0.17
## 4 0.52 0.11 0.11 0.24 0.21
## 5 0.73 0.05 0.14 0.31 0.31
## 6 0.25 0.02 0.05 0.94 1.00
## OwnOccHiQuart RentLowQ RentMedian RentHighQ MedRent MedRentPctHousInc
## 1 0.18 0.36 0.35 0.38 0.34 0.38
## 2 0.21 0.42 0.38 0.40 0.37 0.29
## 3 0.16 0.27 0.29 0.27 0.31 0.48
## 4 0.19 0.75 0.70 0.77 0.89 0.63
## 5 0.30 0.40 0.36 0.38 0.38 0.22
## 6 1.00 0.67 0.63 0.68 0.62 0.47
## MedOwnCostPctInc MedOwnCostPctIncNoMtg NumInShelters NumStreet PctForeignBorn
## 1 0.46 0.25 0.04 0 0.12
## 2 0.32 0.18 0.00 0 0.21
## 3 0.39 0.28 0.00 0 0.14
## 4 0.51 0.47 0.00 0 0.19
## 5 0.51 0.21 0.00 0 0.11
## 6 0.59 0.11 0.00 0 0.70
## PctBornSameState PctSameHouse85 PctSameCity85 PctSameState85 LandArea PopDens
## 1 0.42 0.50 0.51 0.64 0.12 0.26
## 2 0.50 0.34 0.60 0.52 0.02 0.12
## 3 0.49 0.54 0.67 0.56 0.01 0.21
## 4 0.30 0.73 0.64 0.65 0.02 0.39
## 5 0.72 0.64 0.61 0.53 0.04 0.09
## 6 0.42 0.49 0.73 0.64 0.01 0.58
## PctUsePubTrans
## 1 0.20
## 2 0.45
## 3 0.02
## 4 0.28
## 5 0.02
## 6 0.10# La siguiente instrucción construye la variable a predecir
y<-datos$ViolentCrimesPerPoplibrary(glmnet)
datosx<-model.matrix(ViolentCrimesPerPop~.,datos)[,-c(103)]
v.alpha<-c(0,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1)
for(ss in v.alpha) {
cat("========ELASTIC NET========\n")
cat("Alpha=",ss,"\n")
net.mod<-glmnet(x,y,alpha=ss)
sal.cv<-cv.glmnet(x,y,alpha=ss)
mejor.lambda<-sal.cv$lambda.min
pred<-predict(net.mod,s=mejor.lambda,newx=datosx)
res<-MSE(pred,datos$ViolentCrimesPerPop)
cat("MSE",res,"\n")
}## ========ELASTIC NET========
## Alpha= 0
## MSE 0.01720385
## ========ELASTIC NET========
## Alpha= 0.1
## MSE 0.01669266
## ========ELASTIC NET========
## Alpha= 0.2
## MSE 0.01694991
## ========ELASTIC NET========
## Alpha= 0.3
## MSE 0.01674577
## ========ELASTIC NET========
## Alpha= 0.4
## MSE 0.01680713
## ========ELASTIC NET========
## Alpha= 0.5
## MSE 0.01682668
## ========ELASTIC NET========
## Alpha= 0.6
## MSE 0.01675929
## ========ELASTIC NET========
## Alpha= 0.7
## MSE 0.01672877
## ========ELASTIC NET========
## Alpha= 0.8
## MSE 0.01672512
## ========ELASTIC NET========
## Alpha= 0.9
## MSE 0.0167222
## ========ELASTIC NET========
## Alpha= 1
## MSE 0.0167005- ¿Cu´al m´etodo usar´ıa con base en la informaci´on obtenida en los ejercicios anteriores?
En este caso el error cuadratico medio y error relativo mas bajo parece ser nuevamente la regresion de Lasso, la diferencia resulta no muy grande, pero mejor.
Pregunta 4: 1. Programe en R una funci´on lm2(…) que recibe como par´ametro una tabla de aprendizaje y retorna un modelo de Regresi´on Lineal, es decir, calcula y retorna β = (XtX) −1Xt y.
x<-model.matrix(ViolentCrimesPerPop~.,taprendizaje)[,-c(103)]
y<-datos$ViolentCrimesPerPop
lm2<-function(X,Y){
n<-nrow(X)
k<-ncol(X)
Constante<-seq(1,1,length.out =n)
datos1<-data.frame(Constante,X)
X<-as.matrix(datos1)
Y<-as.matrix(Y)
XtX<-t(X)%*%X
XtX.inv<-solve(XtX)
XY<-t(X)%*%Y
Betas<-solve(t(X)%*%X)%*%(t(X)%*%Y)
B<-data.frame(Coeficientes=Betas)
B
}
lm2(datos[,1:102], datos[,103])## Coeficientes
## Constante 0.5987695284
## state -0.0007436828
## fold -0.0015747954
## population 0.1321909463
## householdsize 0.0007521874
## racepctblack 0.2000845595
## racePctWhite -0.0545392566
## racePctAsian -0.0132277730
## racePctHisp 0.0537790097
## agePct12t21 0.1156000167
## agePct12t29 -0.2374790232
## agePct16t24 -0.1330132267
## agePct65up 0.0364240293
## numbUrban -0.2461313866
## pctUrban 0.0468132605
## medIncome -0.1778504926
## pctWWage -0.1977078909
## pctWFarmSelf 0.0466592440
## pctWInvInc -0.1600134323
## pctWSocSec 0.0829735051
## pctWPubAsst -0.0064110991
## pctWRetire -0.0862223022
## medFamInc 0.2783260665
## perCapInc 0.1090832142
## whitePerCap -0.3540081300
## blackPerCap -0.0322051945
## indianPerCap -0.0332265789
## AsianPerCap 0.0198696225
## OtherPerCap 0.0446076633
## HispPerCap 0.0312483584
## NumUnderPov 0.1257067673
## PctPopUnderPov -0.1723615272
## PctLess9thGrade -0.1019432432
## PctNotHSGrad 0.0529293524
## PctBSorMore 0.0548988639
## PctUnemployed 0.0024202568
## PctEmploy 0.2636936643
## PctEmplManu -0.0611584964
## PctEmplProfServ -0.0231200271
## PctOccupManu 0.0725968767
## PctOccupMgmtProf 0.1095694309
## MalePctDivorce 0.4315918094
## MalePctNevMarr 0.2211649847
## FemalePctDiv 0.1139415282
## TotalPctDiv -0.4977382607
## PersPerFam -0.1600699304
## PctFam2Par -0.0143193239
## PctKids2Par -0.2870569326
## PctYoungKids2Par -0.0267124056
## PctTeen2Par -0.0025638736
## PctWorkMomYoungKids 0.0523100472
## PctWorkMom -0.1888669617
## NumIlleg -0.1383370705
## PctIlleg 0.1143173345
## NumImmig -0.1403383194
## PctImmigRecent 0.0221217598
## PctImmigRec5 0.0242018090
## PctImmigRec8 -0.0690847068
## PctImmigRec10 0.0360764526
## PctRecentImmig -0.0244705538
## PctRecImmig5 -0.2037795787
## PctRecImmig8 0.3916333568
## PctRecImmig10 -0.1607643949
## PctSpeakEnglOnly -0.0265884653
## PctNotSpeakEnglWell -0.1367050018
## PctLargHouseFam 0.0572615051
## PctLargHouseOccup -0.1874714841
## PersPerOccupHous 0.5663796516
## PersPerOwnOccHous -0.0452152549
## PersPerRentOccHous -0.2410336539
## PctPersOwnOccup -0.6954981880
## PctPersDenseHous 0.2086599671
## PctHousLess3BR 0.0849001959
## MedNumBR 0.0265379417
## HousVacant 0.1541798393
## PctHousOccup -0.0495126580
## PctHousOwnOcc 0.5636854419
## PctVacantBoarded 0.0543938209
## PctVacMore6Mos -0.0717601786
## MedYrHousBuilt -0.0231801967
## PctHousNoPhone 0.0189780846
## PctWOFullPlumb -0.0139302138
## OwnOccLowQuart -0.3956505825
## OwnOccMedVal 0.2677203447
## OwnOccHiQuart 0.0194529573
## RentLowQ -0.2313898655
## RentMedian -0.0012952529
## RentHighQ -0.0571824169
## MedRent 0.3417753478
## MedRentPctHousInc 0.0424070175
## MedOwnCostPctInc -0.0404555487
## MedOwnCostPctIncNoMtg -0.0739524561
## NumInShelters 0.1343449602
## NumStreet 0.1754496414
## PctForeignBorn 0.1145704673
## PctBornSameState 0.0166478623
## PctSameHouse85 -0.0038043813
## PctSameCity85 0.0190145485
## PctSameState85 0.0134812735
## LandArea 0.0176207904
## PopDens -0.0113546651
## PctUsePubTrans -0.0370162514
## LemasPctOfficDrugUn 0.0244668241- Programe en R una funci´on predict2(…) que recibe como par´ametro el modelo construido en la pregunta anterior, una tabla de testing de modo tal que retorna la predicci´on para esta tabla de testing.
# numero.predictoras <- dim(datos)[2] - 1
# # Hace la Predicción
# prediccion <- predict(modelo.lm, ttesting)
# # Medición de precisión
# pre.lm <- indices.precision(ttesting$ViolentCrimesPerPop, prediccion,numero.predictoras)
# pre.lm
x<-model.matrix(ViolentCrimesPerPop~.,ttesting)[,-c(103)]
y<-datos$ViolentCrimesPerPop
predict2<-function(x,y){
n<-nrow(x)
k<-ncol(x)
Constante<-seq(1,1,length.out =n)
datos1<-data.frame(Constante,x)
X<-as.matrix(datos1)
Y<-as.matrix(y)
XtX<-t(X)%*%X
XtX.inv<-solve(XtX)
XY<-t(X)%*%Y
Betas<-solve(t(X)%*%X)%*%(t(X)%*%Y)
# Suma de Cuadrados
Syy<-t(Y)%*%Y-nrow(Y)*mean(Y)^2
SSE=t(Y)%*%Y - t(Betas)%*%XY
SSR<-t(Betas)%*%XY-nrow(Y)*mean(Y)^2
# Grados de libertad
gl1=k
gl2=nrow(Y)-(k+1)
# test para Betas
MSE=SSE/gl2
Varianzas<-as.vector(MSE)*diag(XtX.inv)
Desviaciones<-sqrt(Varianzas)
diagonal<-diag(Desviaciones,k+1,k+1)
t<-t(t(Betas)%*%solve(diagonal))
v.p<-2*pt(abs(t),gl2,lower.tail=FALSE)
estimaciones<-data.frame(Coeficientes=Betas,t_student = t,Valor_p=v.p)
estimaciones
}
predict2(datos[,1:102], datos[,103])## Coeficientes t_student Valor_p
## Constante 0.5987695284 2.948030360 3.237254e-03
## state -0.0007436828 -2.976976198 2.948044e-03
## fold -0.0015747954 -1.493702715 1.354202e-01
## population 0.1321909463 0.333126648 7.390756e-01
## householdsize 0.0007521874 0.008695378 9.930631e-01
## racepctblack 0.2000845595 3.916548999 9.301525e-05
## racePctWhite -0.0545392566 -0.928818670 3.531016e-01
## racePctAsian -0.0132277730 -0.385534897 6.998845e-01
## racePctHisp 0.0537790097 1.007286857 3.139258e-01
## agePct12t21 0.1156000167 1.093397074 2.743588e-01
## agePct12t29 -0.2374790232 -1.519992547 1.286800e-01
## agePct16t24 -0.1330132267 -0.811150728 4.173812e-01
## agePct65up 0.0364240293 0.352318077 7.246390e-01
## numbUrban -0.2461313866 -0.636496140 5.245301e-01
## pctUrban 0.0468132605 2.998678423 2.746906e-03
## medIncome -0.1778504926 -1.031315916 3.025246e-01
## pctWWage -0.1977078909 -2.210510911 2.718905e-02
## pctWFarmSelf 0.0466592440 2.319567189 2.047034e-02
## pctWInvInc -0.1600134323 -2.363496873 1.820402e-02
## pctWSocSec 0.0829735051 0.775991294 4.378512e-01
## pctWPubAsst -0.0064110991 -0.138978280 8.894821e-01
## pctWRetire -0.0862223022 -2.344545091 1.915327e-02
## medFamInc 0.2783260665 1.737868691 8.239674e-02
## perCapInc 0.1090832142 0.578816542 5.627819e-01
## whitePerCap -0.3540081300 -2.325004146 2.017711e-02
## blackPerCap -0.0322051945 -1.266305516 2.055597e-01
## indianPerCap -0.0332265789 -1.713602469 8.676565e-02
## AsianPerCap 0.0198696225 1.051247432 2.932793e-01
## OtherPerCap 0.0446076633 2.387168751 1.707643e-02
## HispPerCap 0.0312483584 1.258424233 2.083937e-01
## NumUnderPov 0.1257067673 0.911880007 3.619481e-01
## PctPopUnderPov -0.1723615272 -2.749185557 6.031177e-03
## PctLess9thGrade -0.1019432432 -1.504976042 1.324972e-01
## PctNotHSGrad 0.0529293524 0.552540650 5.806433e-01
## PctBSorMore 0.0548988639 0.710047773 4.777621e-01
## PctUnemployed 0.0024202568 0.059471293 9.525830e-01
## PctEmploy 0.2636936643 3.340902695 8.513155e-04
## PctEmplManu -0.0611584964 -1.908903265 5.642581e-02
## PctEmplProfServ -0.0231200271 -0.566713457 5.709761e-01
## PctOccupManu 0.0725968767 1.322024223 1.863200e-01
## PctOccupMgmtProf 0.1095694309 1.270554684 2.040434e-01
## MalePctDivorce 0.4315918094 1.744659031 8.120669e-02
## MalePctNevMarr 0.2211649847 3.257799723 1.142688e-03
## FemalePctDiv 0.1139415282 0.368541220 7.125110e-01
## TotalPctDiv -0.4977382607 -0.961061627 3.366441e-01
## PersPerFam -0.1600699304 -0.950913762 3.417697e-01
## PctFam2Par -0.0143193239 -0.089656207 9.285699e-01
## PctKids2Par -0.2870569326 -1.845595995 6.510712e-02
## PctYoungKids2Par -0.0267124056 -0.554285571 5.794490e-01
## PctTeen2Par -0.0025638736 -0.060208601 9.519959e-01
## PctWorkMomYoungKids 0.0523100472 1.113225238 2.657532e-01
## PctWorkMom -0.1888669617 -3.512753258 4.539057e-04
## NumIlleg -0.1383370705 -1.276631412 2.018892e-01
## PctIlleg 0.1143173345 2.408390497 1.611817e-02
## NumImmig -0.1403383194 -1.801761634 7.174213e-02
## PctImmigRecent 0.0221217598 0.539503302 5.896031e-01
## PctImmigRec5 0.0242018090 0.363968668 7.159221e-01
## PctImmigRec8 -0.0690847068 -0.896133284 3.702956e-01
## PctImmigRec10 0.0360764526 0.605350965 5.450185e-01
## PctRecentImmig -0.0244705538 -0.200481076 8.411259e-01
## PctRecImmig5 -0.2037795787 -0.921567036 3.568720e-01
## PctRecImmig8 0.3916333568 1.433677615 1.518296e-01
## PctRecImmig10 -0.1607643949 -0.734613973 4.626657e-01
## PctSpeakEnglOnly -0.0265884653 -0.378231555 7.053010e-01
## PctNotSpeakEnglWell -0.1367050018 -1.998406580 4.581555e-02
## PctLargHouseFam 0.0572615051 0.253556604 7.998657e-01
## PctLargHouseOccup -0.1874714841 -0.793054630 4.278455e-01
## PersPerOccupHous 0.5663796516 2.262691841 2.376770e-02
## PersPerOwnOccHous -0.0452152549 -0.269618833 7.874829e-01
## PersPerRentOccHous -0.2410336539 -2.979933794 2.919863e-03
## PctPersOwnOccup -0.6954981880 -1.944430238 5.199170e-02
## PctPersDenseHous 0.2086599671 2.761121296 5.815978e-03
## PctHousLess3BR 0.0849001959 1.442889382 1.492173e-01
## MedNumBR 0.0265379417 1.365662098 1.722075e-01
## HousVacant 0.1541798393 2.113030849 3.472884e-02
## PctHousOccup -0.0495126580 -1.600882000 1.095701e-01
## PctHousOwnOcc 0.5636854419 1.507093326 1.319538e-01
## PctVacantBoarded 0.0543938209 2.541694184 1.111089e-02
## PctVacMore6Mos -0.0717601786 -2.853817056 4.366775e-03
## MedYrHousBuilt -0.0231801967 -0.801567303 4.229040e-01
## PctHousNoPhone 0.0189780846 0.538337996 5.904071e-01
## PctWOFullPlumb -0.0139302138 -0.688423152 4.912708e-01
## OwnOccLowQuart -0.3956505825 -1.934866517 5.315565e-02
## OwnOccMedVal 0.2677203447 0.872314314 3.831477e-01
## OwnOccHiQuart 0.0194529573 0.118193677 9.059268e-01
## RentLowQ -0.2313898655 -3.454729518 5.629978e-04
## RentMedian -0.0012952529 -0.008274622 9.933988e-01
## RentHighQ -0.0571824169 -0.663902822 5.068334e-01
## MedRent 0.3417753478 2.636147114 8.453922e-03
## MedRentPctHousInc 0.0424070175 1.303088855 1.927031e-01
## MedOwnCostPctInc -0.0404555487 -1.173834915 2.406090e-01
## MedOwnCostPctIncNoMtg -0.0739524561 -3.002945955 2.708862e-03
## NumInShelters 0.1343449602 2.095238847 3.628247e-02
## NumStreet 0.1754496414 3.725871871 2.003541e-04
## PctForeignBorn 0.1145704673 1.275673208 2.022277e-01
## PctBornSameState 0.0166478623 0.399058443 6.898952e-01
## PctSameHouse85 -0.0038043813 -0.065865085 9.474922e-01
## PctSameCity85 0.0190145485 0.499023424 6.178209e-01
## PctSameState85 0.0134812735 0.316203670 7.518828e-01
## LandArea 0.0176207904 0.359101486 7.195593e-01
## PopDens -0.0113546651 -0.374491636 7.080806e-01
## PctUsePubTrans -0.0370162514 -1.600471863 1.096610e-01
## LemasPctOfficDrugUn 0.0244668241 1.584719873 1.131972e-01- Usando la tabla de datos uscrime.csv compare los resultados de las funciones lm(…), lm2(…), predict(…) y predict2(…).
lm <- lm(ViolentCrimesPerPop~., data = taprendizaje)
lm##
## Call:
## lm(formula = ViolentCrimesPerPop ~ ., data = taprendizaje)
##
## Coefficients:
## (Intercept) state fold
## 0.7301321 -0.0005933 -0.0017368
## population householdsize racepctblack
## -0.0269510 0.1004843 0.1236990
## racePctWhite racePctAsian racePctHisp
## -0.1437003 -0.0136794 0.0632988
## agePct12t21 agePct12t29 agePct16t24
## 0.1643552 -0.1815100 -0.1828198
## agePct65up numbUrban pctUrban
## 0.0195642 -0.1106344 0.0441169
## medIncome pctWWage pctWFarmSelf
## -0.2885981 -0.1594796 0.0302056
## pctWInvInc pctWSocSec pctWPubAsst
## -0.1186551 0.0885469 -0.0189197
## pctWRetire medFamInc perCapInc
## -0.0795092 0.3339612 0.1833208
## whitePerCap blackPerCap indianPerCap
## -0.4143148 -0.0432160 -0.0329392
## AsianPerCap OtherPerCap HispPerCap
## 0.0050798 0.0291808 0.0579221
## NumUnderPov PctPopUnderPov PctLess9thGrade
## 0.1147659 -0.1817281 -0.0572288
## PctNotHSGrad PctBSorMore PctUnemployed
## 0.0424882 0.0315698 0.0096606
## PctEmploy PctEmplManu PctEmplProfServ
## 0.2326172 -0.0813150 -0.0113773
## PctOccupManu PctOccupMgmtProf MalePctDivorce
## 0.0817852 0.0899506 0.3950949
## MalePctNevMarr FemalePctDiv TotalPctDiv
## 0.0998573 0.0525902 -0.4152243
## PersPerFam PctFam2Par PctKids2Par
## -0.2326905 -0.1843596 -0.1693039
## PctYoungKids2Par PctTeen2Par PctWorkMomYoungKids
## -0.0130657 -0.0151195 0.0737985
## PctWorkMom NumIlleg PctIlleg
## -0.2160931 -0.2395280 0.1607720
## NumImmig PctImmigRecent PctImmigRec5
## -0.1207343 0.0516954 0.0117994
## PctImmigRec8 PctImmigRec10 PctRecentImmig
## -0.0904042 0.0762501 -0.0206852
## PctRecImmig5 PctRecImmig8 PctRecImmig10
## -0.4302941 0.5926712 -0.0721819
## PctSpeakEnglOnly PctNotSpeakEnglWell PctLargHouseFam
## -0.0643134 -0.1564434 0.1642796
## PctLargHouseOccup PersPerOccupHous PersPerOwnOccHous
## -0.2961117 0.5282477 0.0516878
## PersPerRentOccHous PctPersOwnOccup PctPersDenseHous
## -0.3074837 -0.9441568 0.1575127
## PctHousLess3BR MedNumBR HousVacant
## 0.0887776 0.0264781 0.2230062
## PctHousOccup PctHousOwnOcc PctVacantBoarded
## -0.0416508 0.7927967 0.0336534
## PctVacMore6Mos MedYrHousBuilt PctHousNoPhone
## -0.0716178 -0.0122728 -0.0202421
## PctWOFullPlumb OwnOccLowQuart OwnOccMedVal
## -0.0210938 -0.1794044 0.0972415
## OwnOccHiQuart RentLowQ RentMedian
## 0.0467856 -0.2278201 -0.1073302
## RentHighQ MedRent MedRentPctHousInc
## 0.0083983 0.3802668 0.0431364
## MedOwnCostPctInc MedOwnCostPctIncNoMtg NumInShelters
## -0.0552143 -0.0512172 0.2211884
## NumStreet PctForeignBorn PctBornSameState
## 0.1516897 0.0156050 -0.0006032
## PctSameHouse85 PctSameCity85 PctSameState85
## 0.0454816 0.0269999 0.0097497
## LandArea PopDens PctUsePubTrans
## 0.0064374 -0.0441963 -0.0510265
## LemasPctOfficDrugUn
## 0.0251963prediccion <- predict(lm, ttesting)
head(prediccion)## 215 1798 723 892 314 998
## 0.07968485 0.12377464 0.23335915 0.09209358 0.42702317 0.15911575- Usando la tabla de datos uscrime.csv y la funci´on de R denominada system.time(…) compare los tiempos de ejecuci´on de las funciones lm(…), lm2(…), predict(…) y predict2(…).
system.time(lm(ViolentCrimesPerPop~., data = taprendizaje))## user system elapsed
## 0.02 0.00 0.03system.time(predict(lm, ttesting))## user system elapsed
## 0 0 0system.time(lm2(datos[,1:102], datos[,103]))## user system elapsed
## 0.03 0.00 0.03system.time(predict2(datos[,1:102], datos[,103]))## user system elapsed
## 0.03 0.00 0.03Es mas rapido lm y predict.
Pregunta 5: Demuestre que la Regresi´on Ridge puede ser obtenida mediante Regresi´on Lineal cl´asica usando una versi´on aumentada de la tabla de datos de la siguiente manera: Se aumenta la tabla de datos X con p filas adicionales √λI; y se aumenta y con p ceros, es decir: Xe =
##Ver arhcivo adjunto
Pregunta 6: (a) Supongamos que ejecutamos una regresi´on Ridge con par´ametro λ en una sola variable X, y se obtiene el coeficiente a. Ahora incluimos una copia exacta X? = X y volvemos a calcular la regresi´on Ridge. Demuestre que ambos coeficientes son id´enticos y calcule su valor. Demuestre en general que si m copias de la variable Xj son incluidas en la regresi´on Ridge, entonces sus coeficientes son todos iguales. Sugerencia: Considere matrices como las siguientes: X =
- ¿Qu´e pasa en Regresi´on Lasso? ¿Ocurre lo mismo?
##Ver arhcivo adjunto
Pregunta 7: En este ejercicio usaremos los datos (voces.csv). Se trata de un problema de reconocimiento de g´enero mediante el an´alisis de la voz y el habla. Esta base de datos fue creada para identificar una voz como masculina o femenina, bas´andose en las propiedades ac´usticas de la voz y el habla. El conjunto de datos consta de 3.168 muestras de voz grabadas, recogidas de hablantes masculinos y femeninos. Las muestras de voz se preprocesan mediante an´alisis
- Cargue la tabla de datos voces.csv en R. No olvide recodificar la variable a predecir como categ´orica.
setwd("C:/Users/rzamoram/Documents/Machine Learning/Mineria de Datos I/Clase3")
datos<-read.csv("voces.csv",dec='.',header=T)
str(datos)## 'data.frame': 3168 obs. of 21 variables:
## $ meanfreq: num 0.0598 0.066 0.0773 0.1512 0.1351 ...
## $ sd : num 0.0642 0.0673 0.0838 0.0721 0.0791 ...
## $ median : num 0.032 0.0402 0.0367 0.158 0.1247 ...
## $ Q25 : num 0.0151 0.0194 0.0087 0.0966 0.0787 ...
## $ Q75 : num 0.0902 0.0927 0.1319 0.208 0.206 ...
## $ IQR : num 0.0751 0.0733 0.1232 0.1114 0.1273 ...
## $ skew : num 12.86 22.42 30.76 1.23 1.1 ...
## $ kurt : num 274.4 634.61 1024.93 4.18 4.33 ...
## $ sp.ent : num 0.893 0.892 0.846 0.963 0.972 ...
## $ sfm : num 0.492 0.514 0.479 0.727 0.784 ...
## $ mode : num 0 0 0 0.0839 0.1043 ...
## $ centroid: num 0.0598 0.066 0.0773 0.1512 0.1351 ...
## $ meanfun : num 0.0843 0.1079 0.0987 0.089 0.1064 ...
## $ minfun : num 0.0157 0.0158 0.0157 0.0178 0.0169 ...
## $ maxfun : num 0.276 0.25 0.271 0.25 0.267 ...
## $ meandom : num 0.00781 0.00901 0.00799 0.2015 0.71281 ...
## $ mindom : num 0.00781 0.00781 0.00781 0.00781 0.00781 ...
## $ maxdom : num 0.00781 0.05469 0.01562 0.5625 5.48438 ...
## $ dfrange : num 0 0.04688 0.00781 0.55469 5.47656 ...
## $ modindx : num 0 0.0526 0.0465 0.2471 0.2083 ...
## $ genero : Factor w/ 2 levels "Femenino","Masculino": 2 2 2 2 2 2 2 2 2 2 ...datos$genero <- factor(datos$genero,ordered = TRUE) ##ya es un factor es una linea repetitiva pero que ordena barplot(prop.table(table(datos$genero)),col=c("orange","blue","green"),main="Distribución de la variable por predecir")
- Usando el comando sample de R genere al azar una tabla aprendizaje con un 80 % de los datos y con el resto de los datos genere una tabla de aprendizaje.
muestra <- sample(1:nrow(datos),floor(nrow(datos)*0.20))
ttesting <- datos[muestra,]
taprendizaje <- datos[-muestra,]
nrow(ttesting)## [1] 633nrow(taprendizaje)## [1] 2535- Usando el m´etodo de Regresi´on Log´ıstica (con glm y glmnet) genere modelos predictivos para la tabla de aprendizaje. Luego para estos modelos calcule la matriz de confusi´on, la precisi´on, la precisi´on positiva, la precisi´on negativa, los falsos positivos, los falsos negativos, la acertividad positiva y la acertividad negativa.
indices.general <- function(MC) {
precision.global <- sum(diag(MC))/sum(MC)
error.global <- 1 - precision.global
precision.categoria <- diag(MC)/rowSums(MC)
precision.positiva <- MC[2, 2]/(MC[2, 2] + MC[2, 1])
precision.negativa <- MC[1, 1]/(MC[1, 1] + MC[1, 2])
falsos.positivos <- 1 - precision.negativa
falsos.negativos <- 1 - precision.positiva
asertividad.positiva <- MC[2, 2]/(MC[1, 2] + MC[2, 2])
asertividad.negativa <- MC[1, 1]/(MC[1, 1] + MC[2, 1])
res <- list(matriz.confusion = MC, precision.global = precision.global, error.global = error.global,
precision.categoria = precision.categoria, precision.positiva = precision.positiva, precision.negativa=precision.negativa,
falsos.positivos=falsos.positivos, falsos.negativos=falsos.negativos, asertividad.positiva=asertividad.positiva,
asertividad.negativa=asertividad.negativa)
names(res) <- c("Matriz de Confusión", "Precisión Global", "Error Global", "Precisión por categoría", "Precision Positiva", "Precision Negativa",
"Falsos Positivos", "Falsos Negativos", "Asertividad Positiva", "Asertividad Negativa")
return(res)
}library(corrplot)
library(glmnet)
library(dygraphs)
library(tidyverse)modelo <- glm(genero ~ . , data = taprendizaje, family = binomial)
probabilidades <- predict(modelo, ttesting, type = "response")## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleadinghead(probabilidades)## 684 2667 2396 1259 2691 1833
## 9.970566e-01 7.745460e-01 3.507848e-05 7.807961e-01 8.550824e-02 6.146585e-04prediccion <- rep("No", dim(ttesting)[1])
prediccion[probabilidades > 0.5] = "Si" # Porque 1=Si entonces P>=0.5 => Si
Actual <- ttesting$genero
## Matriz de Confusión
MC <- table(Actual, prediccion)
indices.general(MC)## $`Matriz de Confusión`
## prediccion
## Actual No Si
## Femenino 323 12
## Masculino 4 294
##
## $`Precisión Global`
## [1] 0.9747235
##
## $`Error Global`
## [1] 0.02527646
##
## $`Precisión por categoría`
## Femenino Masculino
## 0.9641791 0.9865772
##
## $`Precision Positiva`
## [1] 0.9865772
##
## $`Precision Negativa`
## [1] 0.9641791
##
## $`Falsos Positivos`
## [1] 0.0358209
##
## $`Falsos Negativos`
## [1] 0.01342282
##
## $`Asertividad Positiva`
## [1] 0.9607843
##
## $`Asertividad Negativa`
## [1] 0.9877676- Construya una tabla para los ´ındices anteriores que permita comparar el resultados de los m´etodos Regresi´on Log´ıstica Cl´asica, Ridge y Lasso ¿Cu´al m´etodo es mejor? Campare tambi´en con los resultados de las tareas anteriores. ¿Cu´al m´etodo es mejor?
#LASSO
x <- model.matrix(genero ~ ., taprendizaje)[,-1]
head(x)## meanfreq sd median Q25 Q75 IQR skew
## 1 0.05978098 0.06424127 0.03202691 0.015071489 0.09019344 0.07512195 12.863462
## 3 0.07731550 0.08382942 0.03671846 0.008701057 0.13190802 0.12320696 30.757155
## 4 0.15122809 0.07211059 0.15801119 0.096581728 0.20795525 0.11137352 1.232831
## 5 0.13512039 0.07914610 0.12465623 0.078720218 0.20604493 0.12732471 1.101174
## 7 0.15076233 0.07446321 0.16010638 0.092898936 0.20571809 0.11281915 1.530643
## 8 0.16051433 0.07676688 0.14433678 0.110532168 0.23196187 0.12142971 1.397156
## kurt sp.ent sfm mode centroid meanfun minfun
## 1 274.402906 0.8933694 0.4919178 0.00000000 0.05978098 0.08427911 0.01570167
## 3 1024.927705 0.8463891 0.4789050 0.00000000 0.07731550 0.09870626 0.01565558
## 4 4.177296 0.9633225 0.7272318 0.08387819 0.15122809 0.08896485 0.01779755
## 5 4.333713 0.9719551 0.7835681 0.10426140 0.13512039 0.10639784 0.01693122
## 7 5.987498 0.9675731 0.7626377 0.08619681 0.15076233 0.10594452 0.02622951
## 8 4.766611 0.9592546 0.7198579 0.12832407 0.16051433 0.09305243 0.01775805
## maxfun meandom mindom maxdom dfrange modindx
## 1 0.2758621 0.007812500 0.0078125 0.0078125 0.0000000 0.00000000
## 3 0.2711864 0.007990057 0.0078125 0.0156250 0.0078125 0.04651163
## 4 0.2500000 0.201497396 0.0078125 0.5625000 0.5546875 0.24711908
## 5 0.2666667 0.712812500 0.0078125 5.4843750 5.4765625 0.20827389
## 7 0.2666667 0.479619565 0.0078125 5.3125000 5.3046875 0.12399186
## 8 0.1441441 0.301339286 0.0078125 0.5390625 0.5312500 0.28393665y <- taprendizaje$generodatos.test <- model.matrix(genero~.,ttesting)[,-1]
modelo.lasso <- glmnet(x, y, alpha = 1, family = "multinomial")
plot(modelo.lasso,"lambda", label=TRUE)
modelo.lasso.cv <- cv.glmnet(x, y, alpha = 1, family = "multinomial")
plot(modelo.lasso.cv)
mejor.lambda <- modelo.lasso.cv$lambda.min
mejor.lambda## [1] 0.001083261prediccion <- predict(modelo.lasso.cv,datos.test,type="class",s=mejor.lambda)
Actual <- ttesting$genero
## Matriz de Confusión
MC <- table(Actual, prediccion)
# Índices de Calidad de la predicción
indices.general(MC)## $`Matriz de Confusión`
## prediccion
## Actual Femenino Masculino
## Femenino 323 12
## Masculino 4 294
##
## $`Precisión Global`
## [1] 0.9747235
##
## $`Error Global`
## [1] 0.02527646
##
## $`Precisión por categoría`
## Femenino Masculino
## 0.9641791 0.9865772
##
## $`Precision Positiva`
## [1] 0.9865772
##
## $`Precision Negativa`
## [1] 0.9641791
##
## $`Falsos Positivos`
## [1] 0.0358209
##
## $`Falsos Negativos`
## [1] 0.01342282
##
## $`Asertividad Positiva`
## [1] 0.9607843
##
## $`Asertividad Negativa`
## [1] 0.9877676###Ridge
x <- model.matrix(genero ~ ., taprendizaje)[,-1]
head(x)## meanfreq sd median Q25 Q75 IQR skew
## 1 0.05978098 0.06424127 0.03202691 0.015071489 0.09019344 0.07512195 12.863462
## 3 0.07731550 0.08382942 0.03671846 0.008701057 0.13190802 0.12320696 30.757155
## 4 0.15122809 0.07211059 0.15801119 0.096581728 0.20795525 0.11137352 1.232831
## 5 0.13512039 0.07914610 0.12465623 0.078720218 0.20604493 0.12732471 1.101174
## 7 0.15076233 0.07446321 0.16010638 0.092898936 0.20571809 0.11281915 1.530643
## 8 0.16051433 0.07676688 0.14433678 0.110532168 0.23196187 0.12142971 1.397156
## kurt sp.ent sfm mode centroid meanfun minfun
## 1 274.402906 0.8933694 0.4919178 0.00000000 0.05978098 0.08427911 0.01570167
## 3 1024.927705 0.8463891 0.4789050 0.00000000 0.07731550 0.09870626 0.01565558
## 4 4.177296 0.9633225 0.7272318 0.08387819 0.15122809 0.08896485 0.01779755
## 5 4.333713 0.9719551 0.7835681 0.10426140 0.13512039 0.10639784 0.01693122
## 7 5.987498 0.9675731 0.7626377 0.08619681 0.15076233 0.10594452 0.02622951
## 8 4.766611 0.9592546 0.7198579 0.12832407 0.16051433 0.09305243 0.01775805
## maxfun meandom mindom maxdom dfrange modindx
## 1 0.2758621 0.007812500 0.0078125 0.0078125 0.0000000 0.00000000
## 3 0.2711864 0.007990057 0.0078125 0.0156250 0.0078125 0.04651163
## 4 0.2500000 0.201497396 0.0078125 0.5625000 0.5546875 0.24711908
## 5 0.2666667 0.712812500 0.0078125 5.4843750 5.4765625 0.20827389
## 7 0.2666667 0.479619565 0.0078125 5.3125000 5.3046875 0.12399186
## 8 0.1441441 0.301339286 0.0078125 0.5390625 0.5312500 0.28393665y <- taprendizaje$generodatos.test <- model.matrix(genero~.,ttesting)[,-1]
modelo.ridge <- glmnet(x, y, alpha = 1, family = "multinomial")
plot(modelo.ridge,"lambda", label=TRUE)
modelo.ridge.cv <- cv.glmnet(x, y, alpha = 1, family = "multinomial")
plot(modelo.ridge.cv)
mejor.lambda <- modelo.ridge.cv$lambda.min
mejor.lambda## [1] 0.0008993424prediccion <- predict(modelo.ridge.cv,datos.test,type="class",s=mejor.lambda)
Actual <- ttesting$genero
## Matriz de Confusión
MC <- table(Actual, prediccion)
# Índices de Calidad de la predicción
indices.general(MC)## $`Matriz de Confusión`
## prediccion
## Actual Femenino Masculino
## Femenino 323 12
## Masculino 4 294
##
## $`Precisión Global`
## [1] 0.9747235
##
## $`Error Global`
## [1] 0.02527646
##
## $`Precisión por categoría`
## Femenino Masculino
## 0.9641791 0.9865772
##
## $`Precision Positiva`
## [1] 0.9865772
##
## $`Precision Negativa`
## [1] 0.9641791
##
## $`Falsos Positivos`
## [1] 0.0358209
##
## $`Falsos Negativos`
## [1] 0.01342282
##
## $`Asertividad Positiva`
## [1] 0.9607843
##
## $`Asertividad Negativa`
## [1] 0.9877676- Construya una tabla para los ´ındices anteriores que permita comparar el resultados de los m´etodos Regresi´on Log´ıstica Cl´asica, Ridge y Lasso ¿Cu´al m´etodo es mejor? Campare tambi´en con los resultados de las tareas anteriores. ¿Cu´al m´etodo es mejor?
x <- data.frame("Modelo" = c("Regresion Logistica","Ridge","Lasso"), "Precision Global" = c(0.9763033,0.9763033, 0.9763033), "Error Global" = c(0.02369668,0.02369668,0.02369668), "precision positiva" = c(0.9803922, 0.9803922, 0.9803922), "precision negativa" = c(0.9724771, 0.9724771, 0.9724771), "falsos positivos" = c(0.02752294, 0.02752294, 0.02752294), "falsos negativos" = c(0.01960784, 0.01960784, 0.01960784), "asertividad positiva" = c(0.9708738, 0.9708738, 0.9708738), "asertividad negativa" = c(0.9814815, 0.9814815, 0.9814815))
x## Modelo Precision.Global Error.Global precision.positiva
## 1 Regresion Logistica 0.9763033 0.02369668 0.9803922
## 2 Ridge 0.9763033 0.02369668 0.9803922
## 3 Lasso 0.9763033 0.02369668 0.9803922
## precision.negativa falsos.positivos falsos.negativos asertividad.positiva
## 1 0.9724771 0.02752294 0.01960784 0.9708738
## 2 0.9724771 0.02752294 0.01960784 0.9708738
## 3 0.9724771 0.02752294 0.01960784 0.9708738
## asertividad.negativa
## 1 0.9814815
## 2 0.9814815
## 3 0.9814815Los tres modelos curiosamente dan resultados iguales pero analizando la precision global y por categorias estos tres modelos de regresion por igual logran estimar adecuadamente la diferencia en el genero de voz. El metodo trainRSVM “Radial” continua siendo el mas preciso y con menor error global. A pesar de ello bosques aleatorios (0.9763033), potenciaciacion (0.9731438) y xgboosting (0.9794629) se muestran como metodos significativamente precisos, tambien. De hecho, la diferencia respecto al SVM mencionado no resulta significativa. El metodo de Bayes posee el peor desempeno segun la precision global y el error, analizando la matriz de confusion ademas, se denota que este metodo tiene un exceso importante de datos confundidos. El mejor SVM para este ejercicio es con el default kernel, el radial. Posee una precision bastante alta de 0.9873618. Para este ejercicio parece ser el metodo el que mejor se ha ajustado. El arbol de decisio con una precision global de 0.9462875, estuvo mas bajo. Ademas otras estimaciones tardan mas, es decir, redes tarda mas entre mas cantidad de nodos, pero la precision global y el error global en los tres casos de redes se mantienen entre 97 y 98%, y 2% y 3%, respectivamente. De los seis modelos (svm, arbol, 3 redes, kvecinos) tomando precision global como criterio principal y revisando un poco la precision de categorias, SVM radial en este caso tiene la precision mas alta , pero se denota que no existe diferencia significativa, ya que siguiendo la finalidad de este ejercicio se realizan distintas simulaciones para comparar. En la mayoria de los casos la precision de la red neuronal especialmente la de 4 nodos se acerca a la que mejor estimacion de svm radial, pero todas las estimaciones usando k vecinos y redes neuronales con distinta cantidad de nodos, han dado precisiones de entre 96,68% y 98,26% como ocurrio en el de 4 nodos contra 15 nodos, es decir, no se notan diferencias significativas. Los svm con otros kernels tambien han sido bastante acertados, de hecho, puede ser la muestra la que influya en la decision.
Pregunta 8: En esta pregunta utiliza los datos (tumores.csv). Se trata de un conjunto de datos de caracter´ısticas del tumor cerebral que incluye cinco variables de primer orden y ocho de textura y cuatro par´ametros de evaluaci´on de la calidad con el nivel objetivo. La variables son: Media, Varianza, Desviaci´on est´andar, Asimetr´ıa, Kurtosis, Contraste, Energ´ıa, ASM (segundo momento angular), Entrop´ıa, Homogeneidad, Disimilitud, Correlaci´on, Grosor, PSNR (Pico de la relaci´on se˜nal-ruido), SSIM (´Indice de Similitud Estructurada), MSE (Mean Square Error), DC (Coeficiente de Dados) y la variable a predecir tipo (1 = Tumor, 0 = No-Tumor). Realice lo siguiente:
setwd("C:/Users/rzamoram/Documents/Machine Learning/Mineria de Datos I/Clase2")
data2<-read.csv("tumores.csv",dec='.',header=T)
head(data2)## imagen media varianza desviacion.estandar entropia asimetria kurtosis
## 1 Image1 23.448517 2538.9856 50.38835 0.6511741 1.984202 5.421042
## 2 Image2 4.398331 834.8530 28.89382 0.9535317 6.495203 43.349355
## 3 Image3 3.244263 642.0592 25.33889 0.9660645 7.772860 61.756034
## 4 Image4 8.511353 1126.2142 33.55911 0.8687651 3.763142 15.107579
## 5 Image5 21.000793 2235.3170 47.27914 0.6847244 1.936029 4.722343
## 6 Image7 11.350555 998.9722 31.60652 0.7611065 2.533920 7.394586
## contraste energia asm homogeneidad disiminitud correlacion psnr
## 1 181.46771 0.7815569 0.6108312 0.8470333 2.7654114 0.9685761 97.97463
## 2 76.74589 0.9727695 0.9462805 0.9807616 0.5486053 0.9597505 110.34660
## 3 81.75241 0.9801609 0.9607154 0.9850659 0.5404114 0.9442587 112.26630
## 4 362.29121 0.9217862 0.8496899 0.9492953 2.7657252 0.8590271 101.95579
## 5 312.43923 0.8041836 0.6467113 0.8803008 3.0066597 0.9385719 97.63987
## 6 303.94798 0.8542768 0.7297889 0.9023554 3.4405509 0.8664795 99.20658
## ssim mse dc tipo
## 1 0.7770111 0.171163194 0.3039887 1
## 2 0.9779528 0.009913194 0.8390189 1
## 3 0.9853620 0.006371528 0.8497749 1
## 4 0.8810152 0.068437500 0.0000000 0
## 5 0.7663084 0.184878472 0.0000000 0
## 6 0.7948807 0.128888889 0.0000000 0library(caret)## Loading required package: lattice##
## Attaching package: 'caret'## The following object is masked from 'package:purrr':
##
## liftdata2$tipo <- factor(data1$tipo,ordered = TRUE)## Error in factor(data1$tipo, ordered = TRUE): object 'data1' not founddata1 <- data2[,-1]
str(data1)## 'data.frame': 1275 obs. of 17 variables:
## $ media : num 23.45 4.4 3.24 8.51 21 ...
## $ varianza : num 2539 835 642 1126 2235 ...
## $ desviacion.estandar: num 50.4 28.9 25.3 33.6 47.3 ...
## $ entropia : num 0.651 0.954 0.966 0.869 0.685 ...
## $ asimetria : num 1.98 6.5 7.77 3.76 1.94 ...
## $ kurtosis : num 5.42 43.35 61.76 15.11 4.72 ...
## $ contraste : num 181.5 76.7 81.8 362.3 312.4 ...
## $ energia : num 0.782 0.973 0.98 0.922 0.804 ...
## $ asm : num 0.611 0.946 0.961 0.85 0.647 ...
## $ homogeneidad : num 0.847 0.981 0.985 0.949 0.88 ...
## $ disiminitud : num 2.765 0.549 0.54 2.766 3.007 ...
## $ correlacion : num 0.969 0.96 0.944 0.859 0.939 ...
## $ psnr : num 98 110.3 112.3 102 97.6 ...
## $ ssim : num 0.777 0.978 0.985 0.881 0.766 ...
## $ mse : num 0.17116 0.00991 0.00637 0.06844 0.18488 ...
## $ dc : num 0.304 0.839 0.85 0 0 ...
## $ tipo : int 1 1 1 0 0 0 1 1 1 1 ...barplot(prop.table(table(data1$tipo)),col=c("orange","blue","green"),main="Distribución de la variable por predecir")
Ejercicio desbalanceado
intrain <- createDataPartition(
y = data1$tipo,
p = .75,
list = FALSE
)
str(intrain)## int [1:957, 1] 1 2 3 5 6 7 8 9 10 11 ...
## - attr(*, "dimnames")=List of 2
## ..$ : NULL
## ..$ : chr "Resample1"taprendizaje <- data1[ intrain,]
ttesting <- data1[-intrain,]
nrow(taprendizaje)## [1] 957nrow(ttesting)## [1] 318- Usando la funci´on indices.general(…) vista en clase para la tabla de testing calcule la matriz de confusi´on, la precisi´on global, el error global y la precisi´on de cada una de las clases. Construya una tabla para los ´ındices anteriores que permita comparar los resultados de los m´etodos Regresi´on Log´ıstica Cl´asica, Ridge y Lasso. ¿Cu´al m´etodo es mejor? Campare tambi´en con los resultados de las tareas anteriores. ¿Cu´al m´etodo es mejor?
modelo <- glm(tipo ~ . , data = taprendizaje, family = binomial)## Warning: glm.fit: algorithm did not converge## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredprobabilidades <- predict(modelo, ttesting, type = "response")
head(probabilidades)## 4 17 18 25 29 31
## 2.220446e-16 1.000000e+00 1.000000e+00 1.000000e+00 1.000000e+00 1.000000e+00prediccion <- rep("No", dim(ttesting)[1])
prediccion[probabilidades > 0.5] = "Si" # Porque 1=Si entonces P>=0.5 => Si
Actual <- ttesting$tipo
## Matriz de Confusión
MC <- table(Actual, prediccion)
indices.general(MC)## $`Matriz de Confusión`
## prediccion
## Actual No Si
## 0 19 4
## 1 9 286
##
## $`Precisión Global`
## [1] 0.9591195
##
## $`Error Global`
## [1] 0.0408805
##
## $`Precisión por categoría`
## 0 1
## 0.8260870 0.9694915
##
## $`Precision Positiva`
## [1] 0.9694915
##
## $`Precision Negativa`
## [1] 0.826087
##
## $`Falsos Positivos`
## [1] 0.173913
##
## $`Falsos Negativos`
## [1] 0.03050847
##
## $`Asertividad Positiva`
## [1] 0.9862069
##
## $`Asertividad Negativa`
## [1] 0.6785714#LASSO
x <- model.matrix(tipo ~ ., taprendizaje)[,-1]
head(x)## media varianza desviacion.estandar entropia asimetria kurtosis
## 1 23.4485168 2538.98563 50.388348 0.6511741 1.984202 5.421042
## 2 4.3983307 834.85303 28.893823 0.9535317 6.495203 43.349355
## 3 3.2442627 642.05917 25.338886 0.9660645 7.772860 61.756034
## 5 21.0007935 2235.31698 47.279139 0.6847244 1.936029 4.722343
## 6 11.3505554 998.97224 31.606522 0.7611065 2.533920 7.394586
## 7 0.4051361 68.37872 8.269143 0.9947236 20.388025 416.843433
## contraste energia asm homogeneidad disiminitud correlacion psnr
## 1 181.46771 0.7815569 0.6108312 0.8470333 2.7654114 0.9685761 97.97463
## 2 76.74589 0.9727695 0.9462805 0.9807616 0.5486053 0.9597505 110.34660
## 3 81.75241 0.9801609 0.9607154 0.9850659 0.5404114 0.9442587 112.26630
## 5 312.43923 0.8041836 0.6467113 0.8803008 3.0066597 0.9385719 97.63987
## 6 303.94798 0.8542768 0.7297889 0.9023554 3.4405509 0.8664795 99.20658
## 7 17.78916 0.9969317 0.9938728 0.9978846 0.1144003 0.8861440 111.37119
## ssim mse dc
## 1 0.7770111 0.171163194 0.3039887
## 2 0.9779528 0.009913194 0.8390189
## 3 0.9853620 0.006371528 0.8497749
## 5 0.7663084 0.184878472 0.0000000
## 6 0.7948807 0.128888889 0.0000000
## 7 0.9851754 0.007829861 0.4104575y <- taprendizaje$tipodatos.test <- model.matrix(tipo~.,ttesting)[,-1]
modelo.lasso <- glmnet(x, y, alpha = 1, family = "multinomial") ## Warning: from glmnet Fortran code (error code -100); Convergence for 100th
## lambda value not reached after maxit=100000 iterations; solutions for larger
## lambdas returnedplot(modelo.lasso,"lambda", label=TRUE)
modelo.lasso.cv <- cv.glmnet(x, y, alpha = 1, family = "multinomial")## Warning: from glmnet Fortran code (error code -100); Convergence for 100th
## lambda value not reached after maxit=100000 iterations; solutions for larger
## lambdas returned## Warning: from glmnet Fortran code (error code -97); Convergence for 97th lambda
## value not reached after maxit=100000 iterations; solutions for larger lambdas
## returned## Warning: from glmnet Fortran code (error code -98); Convergence for 98th lambda
## value not reached after maxit=100000 iterations; solutions for larger lambdas
## returned## Warning: from glmnet Fortran code (error code -96); Convergence for 96th lambda
## value not reached after maxit=100000 iterations; solutions for larger lambdas
## returned## Warning: from glmnet Fortran code (error code -98); Convergence for 98th lambda
## value not reached after maxit=100000 iterations; solutions for larger lambdas
## returned## Warning: from glmnet Fortran code (error code -92); Convergence for 92th lambda
## value not reached after maxit=100000 iterations; solutions for larger lambdas
## returned## Warning: from glmnet Fortran code (error code -99); Convergence for 99th lambda
## value not reached after maxit=100000 iterations; solutions for larger lambdas
## returned## Warning: from glmnet Fortran code (error code -96); Convergence for 96th lambda
## value not reached after maxit=100000 iterations; solutions for larger lambdas
## returnedplot(modelo.lasso.cv)
mejor.lambda <- modelo.lasso.cv$lambda.min
mejor.lambda## [1] 0.0002184057prediccion <- predict(modelo.lasso.cv,datos.test,type="class",s=mejor.lambda)
Actual <- ttesting$tipo
## Matriz de Confusión
MC <- table(Actual, prediccion)
# Índices de Calidad de la predicción
indices.general(MC)## $`Matriz de Confusión`
## prediccion
## Actual 0 1
## 0 22 1
## 1 9 286
##
## $`Precisión Global`
## [1] 0.9685535
##
## $`Error Global`
## [1] 0.03144654
##
## $`Precisión por categoría`
## 0 1
## 0.9565217 0.9694915
##
## $`Precision Positiva`
## [1] 0.9694915
##
## $`Precision Negativa`
## [1] 0.9565217
##
## $`Falsos Positivos`
## [1] 0.04347826
##
## $`Falsos Negativos`
## [1] 0.03050847
##
## $`Asertividad Positiva`
## [1] 0.9965157
##
## $`Asertividad Negativa`
## [1] 0.7096774###Ridge
x <- model.matrix(tipo ~ ., taprendizaje)[,-1]
head(x)## media varianza desviacion.estandar entropia asimetria kurtosis
## 1 23.4485168 2538.98563 50.388348 0.6511741 1.984202 5.421042
## 2 4.3983307 834.85303 28.893823 0.9535317 6.495203 43.349355
## 3 3.2442627 642.05917 25.338886 0.9660645 7.772860 61.756034
## 5 21.0007935 2235.31698 47.279139 0.6847244 1.936029 4.722343
## 6 11.3505554 998.97224 31.606522 0.7611065 2.533920 7.394586
## 7 0.4051361 68.37872 8.269143 0.9947236 20.388025 416.843433
## contraste energia asm homogeneidad disiminitud correlacion psnr
## 1 181.46771 0.7815569 0.6108312 0.8470333 2.7654114 0.9685761 97.97463
## 2 76.74589 0.9727695 0.9462805 0.9807616 0.5486053 0.9597505 110.34660
## 3 81.75241 0.9801609 0.9607154 0.9850659 0.5404114 0.9442587 112.26630
## 5 312.43923 0.8041836 0.6467113 0.8803008 3.0066597 0.9385719 97.63987
## 6 303.94798 0.8542768 0.7297889 0.9023554 3.4405509 0.8664795 99.20658
## 7 17.78916 0.9969317 0.9938728 0.9978846 0.1144003 0.8861440 111.37119
## ssim mse dc
## 1 0.7770111 0.171163194 0.3039887
## 2 0.9779528 0.009913194 0.8390189
## 3 0.9853620 0.006371528 0.8497749
## 5 0.7663084 0.184878472 0.0000000
## 6 0.7948807 0.128888889 0.0000000
## 7 0.9851754 0.007829861 0.4104575y <- taprendizaje$tipodatos.test <- model.matrix(tipo~.,ttesting)[,-1]
modelo.ridge <- glmnet(x, y, alpha = 1, family = "multinomial") ## Warning: from glmnet Fortran code (error code -100); Convergence for 100th
## lambda value not reached after maxit=100000 iterations; solutions for larger
## lambdas returnedplot(modelo.ridge,"lambda", label=TRUE)
modelo.ridge.cv <- cv.glmnet(x, y, alpha = 1, family = "multinomial")## Warning: from glmnet Fortran code (error code -100); Convergence for 100th
## lambda value not reached after maxit=100000 iterations; solutions for larger
## lambdas returned## Warning: from glmnet Fortran code (error code -99); Convergence for 99th lambda
## value not reached after maxit=100000 iterations; solutions for larger lambdas
## returned## Warning: from glmnet Fortran code (error code -100); Convergence for 100th
## lambda value not reached after maxit=100000 iterations; solutions for larger
## lambdas returned## Warning: from glmnet Fortran code (error code -97); Convergence for 97th lambda
## value not reached after maxit=100000 iterations; solutions for larger lambdas
## returned## Warning: from glmnet Fortran code (error code -93); Convergence for 93th lambda
## value not reached after maxit=100000 iterations; solutions for larger lambdas
## returned## Warning: from glmnet Fortran code (error code -98); Convergence for 98th lambda
## value not reached after maxit=100000 iterations; solutions for larger lambdas
## returned## Warning: from glmnet Fortran code (error code -97); Convergence for 97th lambda
## value not reached after maxit=100000 iterations; solutions for larger lambdas
## returned## Warning: from glmnet Fortran code (error code -95); Convergence for 95th lambda
## value not reached after maxit=100000 iterations; solutions for larger lambdas
## returnedplot(modelo.ridge.cv)
mejor.lambda <- modelo.ridge.cv$lambda.min
mejor.lambda## [1] 0.0003168692prediccion <- predict(modelo.ridge.cv,datos.test,type="class",s=mejor.lambda)
Actual <- ttesting$tipo
## Matriz de Confusión
MC <- table(Actual, prediccion)
# Índices de Calidad de la predicción
indices.general(MC)## $`Matriz de Confusión`
## prediccion
## Actual 0 1
## 0 22 1
## 1 10 285
##
## $`Precisión Global`
## [1] 0.9654088
##
## $`Error Global`
## [1] 0.03459119
##
## $`Precisión por categoría`
## 0 1
## 0.9565217 0.9661017
##
## $`Precision Positiva`
## [1] 0.9661017
##
## $`Precision Negativa`
## [1] 0.9565217
##
## $`Falsos Positivos`
## [1] 0.04347826
##
## $`Falsos Negativos`
## [1] 0.03389831
##
## $`Asertividad Positiva`
## [1] 0.9965035
##
## $`Asertividad Negativa`
## [1] 0.6875Los tres modelos presentan una precision global muy alta por encima de 0,98, de hecho la regresion logistica clasica tiene la precision global mas alta de todos los metodos incluyendo tareas pasadas con 0.9874214, pero tiene igualmente problemas identificando los no tumores al tener una precision por categoria en esto de 0.8750000 frente a un 0.9965986 cuando si es tumor. Lasso y ridge mantienen una precision global 0.9811321 que no tiene diferencia significativa respecto a la logistica. Para el caso de tumores la mejor prediccion, anteriormente fue ser con el metodo de bosques aleatorios con una precision global de 0.9842767, seguido de potenciacion con 0.9811321. Cabe resaltar que XGBoosting no logra distinguir bien la variacion en el problema y tiene la peor precision. Cabe destacar tambien que la precision por categoria es alta cuando existe tumor pero de menos de 0,90 cuando no hay tumor. Esto realmente siguiendo los resultados de tareas anteriores que falta datos de no tumores. El segundo peor metodo es el de BayesNinguno estimado, ademas LDA y QDA no estaban logrando ser estimados. Cabe resaltar que por tratarse de tumores los metodos en general no estan logrando estimar correctamente los casos de no tumor.Todos los kernels dan la misma matrix de confusion en el caso de SVM, excepto el linear que permite identificar ambos casos y tiene la precision global mas alta con 0.9716981, pero una asertividad negativa aun baja de 0.7777778.Comparando de forma sencillo los modelos mas acertados en las tareas anteriores, ya que se han dado varios intentos con resultados de toda clase. El SVM linear parece ser en este ejercicio el que mejor esta asimilando los datos para explicar la variabilidad del caso. Tiene una precision global bastante alta. De hecho, todos los casos probables de no tumor los identifica. Aun asi debe indicarse que se trata con tumores, lo implica que se necesita replantear el modelo, dado que se trata de tumores, lo que es mas importante, es probable que se requier un tamano de muestra mas grande para arrojar datos veridicos ya que en este caso los modelos no estan leyendo completamente bien los casos. En el caso de todos los modelos la precision por categoria ha sido especialmente debil al no detectar los no tumores, esto se explica probablemente por la falta de muestra en estos casos.
Pregunta 9: En este ejercicio vamos a predecir n´umeros escritos a mano (Hand Written Digit Recognition), la tabla de de datos est´a en el archivo ZipData 2020.csv. En la figura siguiente se ilustran los datos:
- Cargue la tabla de datos ZipData 2020.csv en R.
setwd("C:/Users/rzamoram/Documents/Machine Learning/Mineria de Datos I/Clase3")
data2<-read.csv("ZipData_2020.csv",sep=";",dec='.',header=T)
head(data2)## Numero V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12
## 1 seis -1 -1 -1 -1.000 -1.000 -1.000 -1.000 -0.631 0.862 -0.167 -1.000
## 2 cinco -1 -1 -1 -0.813 -0.671 -0.809 -0.887 -0.671 -0.853 -1.000 -1.000
## 3 cuatro -1 -1 -1 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.996 0.147
## 4 siete -1 -1 -1 -1.000 -1.000 -0.273 0.684 0.960 0.450 -0.067 -0.679
## 5 tres -1 -1 -1 -1.000 -1.000 -0.928 -0.204 0.751 0.466 0.234 -0.809
## 6 seis -1 -1 -1 -1.000 -1.000 -0.397 0.983 -0.535 -1.000 -1.000 -1.000
## V13 V14 V15 V16 V17 V18 V19 V20 V21 V22 V23 V24
## 1 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000 -1.000 -1.000 -0.992
## 2 -0.774 -0.180 0.052 -0.241 -1 -1 -1 -1 0.392 1.000 0.857 0.727
## 3 1.000 -0.189 -1.000 -1.000 -1 -1 -1 -1 -1.000 -1.000 -1.000 -1.000
## 4 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000 -0.114 0.974 0.917
## 5 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000 -0.370 0.739 1.000
## 6 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000 -1.000 0.692 0.536
## V25 V26 V27 V28 V29 V30 V31 V32 V33 V34 V35 V36
## 1 0.297 1.000 0.307 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1
## 2 1.000 0.805 0.613 0.613 0.860 1.000 1.000 0.396 -1 -1 -1 -1
## 3 -1.000 -1.000 -0.882 1.000 0.390 -0.811 -1.000 -1.000 -1 -1 -1 -1
## 4 0.734 0.994 1.000 0.973 0.391 -0.421 -0.976 -1.000 -1 -1 -1 -1
## 5 1.000 1.000 1.000 0.644 -0.890 -1.000 -1.000 -1.000 -1 -1 -1 -1
## 6 -0.767 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1
## V37 V38 V39 V40 V41 V42 V43 V44 V45 V46 V47
## 1 -1.000 -1.000 -1.000 -0.410 1.000 0.986 -0.565 -1.000 -1.000 -1 -1.000
## 2 -0.548 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1 1.000
## 3 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.715 1.000 0.029 -1 -1.000
## 4 -0.323 0.991 0.622 -0.738 -1.000 -0.639 0.023 0.871 1.000 1 -0.432
## 5 -1.000 0.616 1.000 0.688 -0.455 -0.731 0.659 1.000 -0.287 -1 -1.000
## 6 -1.000 -0.921 0.928 -0.118 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1.000
## V48 V49 V50 V51 V52 V53 V54 V55 V56 V57 V58 V59
## 1 -1.000 -1.000 -1 -1 -1 -1.000 -1.000 -0.683 0.825 1 0.562 -1.000
## 2 0.875 -0.957 -1 -1 -1 -0.786 0.961 1.000 1.000 1 0.727 0.403
## 3 -1.000 -1.000 -1 -1 -1 -1.000 -0.888 -0.912 -1.000 -1 -1.000 -0.549
## 4 -1.000 -1.000 -1 -1 -1 0.409 1.000 0.000 -1.000 -1 -1.000 -1.000
## 5 -1.000 -1.000 -1 -1 -1 -1.000 -0.376 -0.186 -0.874 -1 -1.000 -0.014
## 6 -1.000 -1.000 -1 -1 -1 -1.000 -0.394 1.000 -0.596 -1 -1.000 -1.000
## V60 V61 V62 V63 V64 V65 V66 V67 V68 V69 V70 V71
## 1 -1.000 -1.000 -1.000 -1.000 -1.00 -1 -1 -1 -1.000 -1.000 -0.938 0.540
## 2 0.403 0.171 -0.314 -0.314 -0.94 -1 -1 -1 -1.000 -0.298 1.000 1.000
## 3 1.000 0.361 -1.000 -1.000 -1.00 -1 -1 -1 -1.000 -0.938 0.694 0.057
## 4 -0.842 0.714 1.000 -0.534 -1.00 -1 -1 -1 -0.879 0.965 1.000 -0.713
## 5 1.000 -0.253 -1.000 -1.000 -1.00 -1 -1 -1 -1.000 -1.000 -1.000 -1.000
## 6 -1.000 -1.000 -1.000 -1.000 -1.00 -1 -1 -1 -1.000 -1.000 0.060 0.900
## V72 V73 V74 V75 V76 V77 V78 V79 V80 V81 V82 V83
## 1 1.000 0.778 -0.715 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1
## 2 1.000 0.440 0.056 -0.755 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1
## 3 -1.000 -1.000 -1.000 -0.382 1.000 0.511 -1.000 -1.000 -1 -1 -1 -1
## 4 -1.000 -1.000 -1.000 -1.000 -0.606 0.977 0.695 -0.906 -1 -1 -1 -1
## 5 -1.000 -1.000 -0.978 0.501 1.000 -0.540 -1.000 -1.000 -1 -1 -1 -1
## 6 -0.951 -1.000 -1.000 -1.000 -0.647 0.455 -0.333 -1.000 -1 -1 -1 -1
## V84 V85 V86 V87 V88 V89 V90 V91 V92 V93 V94
## 1 -1.000 -1.000 0.100 1.000 0.922 -0.439 -1.000 -1.000 -1.000 -1.000 -1.000
## 2 -1.000 0.366 1.000 1.000 1.000 1.000 1.000 0.889 -0.081 -0.920 -1.000
## 3 -1.000 -0.311 1.000 -0.043 -1.000 -1.000 -1.000 -0.648 1.000 0.644 -1.000
## 4 -0.528 1.000 0.931 -0.888 -1.000 -1.000 -1.000 -0.949 0.559 0.984 -0.363
## 5 -1.000 -1.000 -1.000 -0.998 -0.341 0.296 0.371 1.000 0.417 -0.989 -1.000
## 6 -1.000 -1.000 0.259 0.676 -1.000 -1.000 -1.000 -0.984 0.677 0.981 0.551
## V95 V96 V97 V98 V99 V100 V101 V102 V103 V104 V105 V106 V107
## 1 -1 -1 -1 -1 -1 -1.00 -0.257 0.950 1.000 -0.162 -1.000 -1.00 -1.000
## 2 -1 -1 -1 -1 -1 -1.00 -0.396 0.886 0.974 0.851 0.851 0.95 1.000
## 3 -1 -1 -1 -1 -1 -1.00 0.489 1.000 -0.493 -1.000 -1.000 -1.00 -0.564
## 4 -1 -1 -1 -1 -1 -0.97 -0.266 -0.555 -1.000 -1.000 -1.000 -1.00 -0.186
## 5 -1 -1 -1 -1 -1 -1.00 -1.000 -1.000 -0.008 1.000 1.000 1.00 1.000
## 6 -1 -1 -1 -1 -1 -1.00 -0.994 0.699 0.305 -1.000 -1.000 -1.00 -0.499
## V108 V109 V110 V111 V112 V113 V114 V115 V116 V117 V118 V119
## 1 -0.987 -0.714 -0.832 -1 -1 -1 -1 -1 -0.797 0.909 1.000 0.300
## 2 1.000 0.539 -0.754 -1 -1 -1 -1 -1 -1.000 -1.000 -0.886 -0.505
## 3 1.000 0.693 -1.000 -1 -1 -1 -1 -1 -0.966 0.988 1.000 -0.893
## 4 1.000 0.488 -1.000 -1 -1 -1 -1 -1 -1.000 -1.000 -1.000 -1.000
## 5 0.761 -0.731 -1.000 -1 -1 -1 -1 -1 -1.000 -1.000 -1.000 0.242
## 6 1.000 -0.092 0.751 -1 -1 -1 -1 -1 -1.000 -0.923 0.966 -0.107
## V120 V121 V122 V123 V124 V125 V126 V127 V128 V129 V130 V131
## 1 -0.961 -1 -1.000 -0.550 0.485 0.996 0.867 0.092 -1 -1 -1 -1
## 2 -1.000 -1 -0.649 0.405 1.000 1.000 0.653 -0.838 -1 -1 -1 -1
## 3 -1.000 -1 -1.000 -0.397 1.000 0.903 -0.977 -1.000 -1 -1 -1 -1
## 4 -1.000 -1 -1.000 0.697 0.992 -0.458 -1.000 -1.000 -1 -1 -1 -1
## 5 1.000 1 0.319 0.259 1.000 0.742 -0.757 -1.000 -1 -1 -1 -1
## 6 -1.000 -1 -1.000 -0.300 0.854 -0.382 0.617 -1.000 -1 -1 -1 -1
## V132 V133 V134 V135 V136 V137 V138 V139 V140 V141 V142
## 1 0.278 1.000 0.877 -0.824 -1.000 -0.905 0.145 0.977 1.000 1.000 1.000
## 2 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.550 0.993 1.000
## 3 -0.559 1.000 1.000 -0.297 -1.000 -1.000 -1.000 -0.611 1.000 0.873 -0.698
## 4 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.341 1.000 0.608 -1.000 -1.000
## 5 -1.000 -1.000 -1.000 -0.975 -0.467 -0.989 -1.000 -1.000 -0.171 0.998 0.669
## 6 -1.000 -0.409 1.000 -0.529 -1.000 -1.000 -1.000 0.048 0.614 -0.268 0.544
## V143 V144 V145 V146 V147 V148 V149 V150 V151 V152 V153
## 1 0.990 -0.745 -1 -1.00 -0.950 0.847 1.000 0.327 -1.000 -1.000 0.355
## 2 0.618 -0.869 -1 -0.96 -0.512 0.134 -0.343 -0.796 -1.000 -1.000 -1.000
## 3 -0.552 -1.000 -1 -1.00 -1.000 -0.126 1.000 1.000 0.766 -0.764 -1.000
## 4 -1.000 -1.000 -1 -1.00 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000
## 5 -0.945 -1.000 -1 -1.00 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000
## 6 -1.000 -1.000 -1 -1.00 -1.000 -1.000 0.050 0.971 -0.839 -1.000 -1.000
## V154 V155 V156 V157 V158 V159 V160 V161 V162 V163 V164
## 1 1.000 0.655 -0.109 -0.185 1.000 0.988 -0.723 -1 -1.000 -0.63 1.000
## 2 -1.000 -1.000 -1.000 -0.432 0.994 1.000 0.223 -1 0.426 1.00 1.000
## 3 -1.000 -0.577 1.000 0.933 0.484 -0.197 -1.000 -1 -1.000 -1.00 -0.818
## 4 0.471 0.998 -0.416 -1.000 -1.000 -1.000 -1.000 -1 -1.000 -1.00 -1.000
## 5 -1.000 -1.000 -1.000 0.228 1.000 0.038 -1.000 -1 -1.000 -1.00 -1.000
## 6 -1.000 0.172 0.526 -0.003 0.307 -1.000 -1.000 -1 -1.000 -1.00 -1.000
## V165 V166 V167 V168 V169 V170 V171 V172 V173 V174 V175
## 1 1.000 0.068 -0.925 0.113 0.960 0.308 -0.884 -1.000 -0.075 1.000 0.641
## 2 1.000 0.214 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 0.292 1.000
## 3 -0.355 0.334 1.000 0.868 -0.289 -0.677 -0.596 1.000 1.000 1.000 -0.581
## 4 -1.000 -1.000 -1.000 -1.000 -0.644 0.963 0.590 -0.999 -1.000 -1.000 -1.000
## 5 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.826 0.918 0.933
## 6 0.398 0.459 -1.000 -1.000 -1.000 -1.000 0.372 0.555 0.520 -0.045 -1.000
## V176 V177 V178 V179 V180 V181 V182 V183 V184 V185 V186
## 1 -0.995 -1.00 -1.000 -0.677 1.000 1.000 0.753 0.341 1 0.707 -0.942
## 2 0.967 -0.88 0.449 1.000 0.896 -0.094 -0.750 -1.000 -1 -1.000 -1.000
## 3 -1.000 -1.00 -1.000 -1.000 -1.000 -1.000 -0.954 0.118 1 1.000 1.000
## 4 -1.000 -1.00 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1 0.061 1.000
## 5 -0.794 -1.00 -1.000 -1.000 -0.666 0.337 0.224 -0.908 -1 -1.000 -1.000
## 6 -1.000 -1.00 -1.000 -1.000 -1.000 0.671 0.176 -1.000 -1 -1.000 -1.000
## V187 V188 V189 V190 V191 V192 V193 V194 V195 V196 V197
## 1 -1.000 -1.000 0.545 1.000 0.027 -1.000 -1.000 -1.000 -0.903 0.792 1.000
## 2 -1.000 -1.000 -1.000 -0.627 1.000 1.000 0.198 -0.105 1.000 1.000 1.000
## 3 1.000 1.000 0.973 -0.092 -0.995 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000
## 4 -0.079 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000
## 5 -1.000 -1.000 -1.000 0.418 1.000 -0.258 -1.000 -1.000 -0.246 1.000 1.000
## 6 0.236 0.934 0.971 -0.712 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 0.763
## V198 V199 V200 V201 V202 V203 V204 V205 V206 V207 V208
## 1 1.000 1.000 1.000 0.536 0.184 0.812 0.837 0.978 0.864 -0.630 -1.000
## 2 0.639 -0.168 -0.314 -0.446 -1.000 -1.000 -0.999 -0.337 0.147 0.996 1.000
## 3 -1.000 -0.993 -0.464 0.046 0.290 0.457 1.000 0.721 -1.000 -1.000 -1.000
## 4 -1.000 -1.000 -1.000 0.773 0.958 -0.714 -1.000 -1.000 -1.000 -1.000 -1.000
## 5 0.355 -0.958 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.077 1.000 0.344
## 6 0.084 -1.000 -1.000 -1.000 -1.000 0.073 1.000 0.265 -1.000 -1.000 -1.000
## V209 V210 V211 V212 V213 V214 V215 V216 V217 V218 V219
## 1 -1.000 -1.000 -1.000 -0.452 0.828 1.000 1.000 1.000 1.000 1.000 1.000
## 2 0.667 -0.808 0.065 0.993 1.000 1.000 1.000 1.000 0.996 0.970 0.970
## 3 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.426
## 4 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.545 0.989 0.432 -1.000
## 5 -1.000 -1.000 0.075 1.000 1.000 0.649 0.256 -0.200 -0.351 -0.733 -0.733
## 6 -1.000 -1.000 -1.000 -1.000 0.563 0.210 -1.000 -1.000 -0.930 -0.127 0.890
## V220 V221 V222 V223 V224 V225 V226 V227 V228 V229 V230
## 1 1.000 1.000 0.135 -1 -1.000 -1.000 -1 -1.000 -1.000 -0.483 0.813
## 2 0.970 0.998 1.000 1 1.000 0.109 -1 -1.000 -0.830 -0.242 0.350
## 3 1.000 0.555 -1.000 -1 -1.000 -1.000 -1 -1.000 -1.000 -1.000 -1.000
## 4 -1.000 -1.000 -1.000 -1 -1.000 -1.000 -1 -1.000 -1.000 -1.000 -1.000
## 5 -0.733 -0.433 0.649 1 0.093 -1.000 -1 -0.959 -0.062 0.821 1.000
## 6 0.935 -0.845 -1.000 -1 -1.000 -1.000 -1 -1.000 -1.000 0.093 0.793
## V231 V232 V233 V234 V235 V236 V237 V238 V239 V240 V241
## 1 1.000 1.000 1.000 1.000 1.000 1.000 0.219 -0.943 -1.000 -1.000 -1.00
## 2 0.800 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 0.616 -0.93
## 3 -1.000 -1.000 -1.000 -1.000 0.024 1.000 0.388 -1.000 -1.000 -1.000 -1.00
## 4 -1.000 -0.348 1.000 0.798 -0.935 -1.000 -1.000 -1.000 -1.000 -1.000 -1.00
## 5 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 0.583 -0.843 -1.00
## 6 -0.205 0.214 0.746 0.918 0.692 0.954 -0.882 -1.000 -1.000 -1.000 -1.00
## V242 V243 V244 V245 V246 V247 V248 V249 V250 V251 V252 V253
## 1 -1 -1 -1 -1.000 -0.974 -0.429 0.304 0.823 1.000 0.482 -0.474 -0.991
## 2 -1 -1 -1 -1.000 -1.000 -0.858 -0.671 -0.671 -0.033 0.761 0.762 0.126
## 3 -1 -1 -1 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.109 1.000 -0.179
## 4 -1 -1 -1 -1.000 -1.000 -1.000 -0.318 1.000 0.536 -0.987 -1.000 -1.000
## 5 -1 -1 -1 -0.877 -0.326 0.174 0.466 0.639 1.000 1.000 0.791 0.439
## 6 -1 -1 -1 -0.898 0.323 1.000 0.803 0.015 -0.862 -0.871 -0.437 -1.000
## V254 V255 V256 V257
## 1 -1.000 -1.000 -1.000 -1
## 2 -0.095 -0.671 -0.828 -1
## 3 -1.000 -1.000 -1.000 -1
## 4 -1.000 -1.000 -1.000 -1
## 5 -0.199 -0.883 -1.000 -1
## 6 -1.000 -1.000 -1.000 -1str(data2)## 'data.frame': 9298 obs. of 257 variables:
## $ Numero: Factor w/ 10 levels "cero","cinco",..: 7 2 3 8 9 7 9 10 1 10 ...
## $ V2 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V3 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V4 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V5 : num -1 -0.813 -1 -1 -1 -1 -0.83 -1 -1 -1 ...
## $ V6 : num -1 -0.671 -1 -1 -1 -1 0.442 -1 -1 -1 ...
## $ V7 : num -1 -0.809 -1 -0.273 -0.928 -0.397 1 -1 -0.454 -1 ...
## $ V8 : num -1 -0.887 -1 0.684 -0.204 0.983 1 -1 0.879 -1 ...
## $ V9 : num -0.631 -0.671 -1 0.96 0.751 -0.535 0.479 0.51 -0.745 -0.909 ...
## $ V10 : num 0.862 -0.853 -1 0.45 0.466 -1 -0.328 -0.213 -1 0.801 ...
## $ V11 : num -0.167 -1 -0.996 -0.067 0.234 -1 -0.947 -1 -1 -0.899 ...
## $ V12 : num -1 -1 0.147 -0.679 -0.809 -1 -1 -1 -1 -1 ...
## $ V13 : num -1 -0.774 1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V14 : num -1 -0.18 -0.189 -1 -1 -1 -1 -1 -1 -1 ...
## $ V15 : num -1 0.052 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V16 : num -1 -0.241 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V17 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V18 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V19 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V20 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V21 : num -1 0.392 -1 -1 -1 -1 -0.025 -1 -1 -1 ...
## $ V22 : num -1 1 -1 -0.114 -0.37 -1 0.519 -1 -0.716 -1 ...
## $ V23 : num -1 0.857 -1 0.974 0.739 0.692 0.124 -1 0.804 -1 ...
## $ V24 : num -0.992 0.727 -1 0.917 1 0.536 0.339 -1 1 -1 ...
## $ V25 : num 0.297 1 -1 0.734 1 -0.767 0.762 0.292 0.42 -0.405 ...
## $ V26 : num 1 0.805 -1 0.994 1 -1 1 0.792 -0.664 1 ...
## $ V27 : num 0.307 0.613 -0.882 1 1 -1 0.456 -0.987 -1 -0.396 ...
## $ V28 : num -1 0.613 1 0.973 0.644 -1 -0.707 -1 -1 -1 ...
## $ V29 : num -1 0.86 0.39 0.391 -0.89 -1 -1 -1 -1 -1 ...
## $ V30 : num -1 1 -0.811 -0.421 -1 -1 -1 -1 -1 -1 ...
## $ V31 : num -1 1 -1 -0.976 -1 -1 -1 -1 -1 -1 ...
## $ V32 : num -1 0.396 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V33 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V34 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V35 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V36 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V37 : num -1 -0.548 -1 -0.323 -1 -1 -1 -1 -0.978 -1 ...
## $ V38 : num -1 1 -1 0.991 0.616 -0.921 -1 -1 0.713 -1 ...
## $ V39 : num -1 1 -1 0.622 1 0.928 -1 -1 1 -1 ...
## $ V40 : num -0.41 1 -1 -0.738 0.688 -0.118 -1 -1 0.027 -1 ...
## $ V41 : num 1 1 -1 -1 -0.455 -1 -0.965 0.56 0.408 -0.072 ...
## $ V42 : num 0.986 1 -1 -0.639 -0.731 -1 -0.086 0.975 0.947 1 ...
## $ V43 : num -0.565 1 -0.715 0.023 0.659 -1 0.843 -0.873 0.56 -0.468 ...
## $ V44 : num -1 1 1 0.871 1 -1 0.681 -1 -0.538 -1 ...
## $ V45 : num -1 1 0.029 1 -0.287 -1 -0.955 -1 -1 -1 ...
## $ V46 : num -1 1 -1 1 -1 -1 -1 -1 -1 -1 ...
## $ V47 : num -1 1 -1 -0.432 -1 -1 -1 -1 -1 -1 ...
## $ V48 : num -1 0.875 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V49 : num -1 -0.957 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V50 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V51 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V52 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V53 : num -1 -0.786 -1 0.409 -1 -1 -1 -1 -0.118 -1 ...
## $ V54 : num -1 0.961 -0.888 1 -0.376 -0.394 -1 -1 1 -1 ...
## $ V55 : num -0.683 1 -0.912 0 -0.186 1 -1 -1 0.665 -1 ...
## $ V56 : num 0.825 1 -1 -1 -0.874 -0.596 -1 -1 -0.902 -1 ...
## $ V57 : num 1 1 -1 -1 -1 -1 -1 0.745 -0.969 0.057 ...
## $ V58 : num 0.562 0.727 -1 -1 -1 -1 -1 0.999 -0.36 1 ...
## $ V59 : num -1 0.403 -0.549 -1 -0.014 -1 -0.467 -0.748 0.805 -0.623 ...
## $ V60 : num -1 0.403 1 -0.842 1 -1 1 -1 0.987 -1 ...
## $ V61 : num -1 0.171 0.361 0.714 -0.253 -1 -0.279 -1 0.327 -1 ...
## $ V62 : num -1 -0.314 -1 1 -1 -1 -1 -1 -0.797 -1 ...
## $ V63 : num -1 -0.314 -1 -0.534 -1 -1 -1 -1 -1 -1 ...
## $ V64 : num -1 -0.94 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V65 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V66 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V67 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V68 : num -1 -1 -1 -0.879 -1 -1 -1 -1 -0.935 -1 ...
## $ V69 : num -1 -0.298 -0.938 0.965 -1 -1 -1 -1 0.764 -1 ...
## $ V70 : num -0.938 1 0.694 1 -1 0.06 -1 -1 1 -1 ...
## $ V71 : num 0.54 1 0.057 -0.713 -1 0.9 -1 -1 -0.367 -1 ...
## $ V72 : num 1 1 -1 -1 -1 -0.951 -1 -1 -1 -1 ...
## $ V73 : num 0.778 0.44 -1 -1 -1 -1 -1 0.596 -1 0.288 ...
## $ V74 : num -0.715 0.056 -1 -1 -0.978 -1 -1 1 -1 1 ...
## $ V75 : num -1 -0.755 -0.382 -1 0.501 -1 -0.719 -0.601 -0.914 -0.683 ...
## $ V76 : num -1 -1 1 -0.606 1 -0.647 1 -1 -0.256 -1 ...
## $ V77 : num -1 -1 0.511 0.977 -0.54 0.455 -0.203 -1 0.833 -1 ...
## $ V78 : num -1 -1 -1 0.695 -1 -0.333 -1 -1 0.778 -1 ...
## $ V79 : num -1 -1 -1 -0.906 -1 -1 -1 -1 -0.22 -1 ...
## $ V80 : num -1 -1 -1 -1 -1 -1 -1 -1 -0.992 -1 ...
## $ V81 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V82 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V83 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V84 : num -1 -1 -1 -0.528 -1 -1 -1 -1 -0.256 -1 ...
## $ V85 : num -1 0.366 -0.311 1 -1 -1 -1 -1 1 -1 ...
## $ V86 : num 0.1 1 1 0.931 -1 0.259 -1 -1 0.538 -1 ...
## $ V87 : num 1 1 -0.043 -0.888 -0.998 0.676 -1 -1 -0.986 -1 ...
## $ V88 : num 0.922 1 -1 -1 -0.341 -1 -1 -1 -1 -1 ...
## $ V89 : num -0.439 1 -1 -1 0.296 -1 -1 0.714 -1 0.253 ...
## $ V90 : num -1 1 -1 -1 0.371 -1 -0.786 1 -1 1 ...
## $ V91 : num -1 0.889 -0.648 -0.949 1 -0.984 0.504 -0.585 -1 -0.647 ...
## $ V92 : num -1 -0.081 1 0.559 0.417 0.677 0.945 -1 -1 -1 ...
## $ V93 : num -1 -0.92 0.644 0.984 -0.989 0.981 -0.801 -1 -0.837 -1 ...
## $ V94 : num -1 -1 -1 -0.363 -1 0.551 -1 -1 0.551 -1 ...
## $ V95 : num -1 -1 -1 -1 -1 -1 -1 -1 1 -1 ...
## $ V96 : num -1 -1 -1 -1 -1 -1 -1 -1 -0.285 -1 ...
## $ V97 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V98 : num -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
## $ V99 : num -1 -1 -1 -1 -1 -1 -1 -1 -0.936 -1 ...
## [list output truncated]barplot(prop.table(table(data2$Numero)), main="Distribución de la variable por predecir")
- Usando los m´etodos Regresi´on Log´ıstica Cl´asica, Ridge y Lasso genere un modelos predictivos y los par´ametros que usted considere m´as conveniente para generar un modelo predictivo para la tabla ZipData 2020.csv usando el 80 % de los datos para la tabla aprendizaje y un 20 % para la tabla testing, luego calcule para los datos de testing la matriz de confusi´on, la precisi´on global y la precisi´on para cada una de las categor´ıas. ¿Son buenos los resultados? Explique.
muestra <- sample(1:nrow(data2),floor(nrow(data2)*0.20))
ttesting <- data2[muestra,]
taprendizaje <- data2[-muestra,]
nrow(ttesting)## [1] 1859nrow(taprendizaje)## [1] 7439modelo <- glm(Numero ~ . , data = taprendizaje, family = binomial)## Warning: glm.fit: algorithm did not converge## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredprobabilidades <- predict(modelo, ttesting, type = "response")
head(probabilidades)## 8624 6808 7274 3516 6821 2152
## 1 1 1 1 1 1prediccion <- rep("No", dim(ttesting)[1])
prediccion[probabilidades > 0.5] = "Si" # Porque 1=Si entonces P>=0.5 => Si
Actual <- ttesting$Numero
## Matriz de Confusión
MC <- table(Actual, prediccion)
indices.general(MC)## $`Matriz de Confusión`
## prediccion
## Actual No Si
## cero 304 17
## cinco 1 126
## cuatro 2 156
## dos 5 191
## nueve 1 155
## ocho 6 134
## seis 6 140
## siete 2 167
## tres 8 174
## uno 0 264
##
## $`Precisión Global`
## [1] 0.2313072
##
## $`Error Global`
## [1] 0.7686928
##
## $`Precisión por categoría`
## cero cinco cuatro dos nueve ocho seis siete
## 0.9470405 0.9921260 1.9240506 0.6428571 1.9487179 0.9000000 2.0821918 0.7455621
## tres uno
## 1.6703297 0.4772727
##
## $`Precision Positiva`
## [1] 0.992126
##
## $`Precision Negativa`
## [1] 0.9470405
##
## $`Falsos Positivos`
## [1] 0.0529595
##
## $`Falsos Negativos`
## [1] 0.007874016
##
## $`Asertividad Positiva`
## [1] 0.8811189
##
## $`Asertividad Negativa`
## [1] 0.9967213#LASSO
x <- model.matrix(Numero ~ ., taprendizaje)[,-1]
head(x)## V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13
## 1 -1 -1 -1 -1.000 -1.000 -1.000 -1.000 -0.631 0.862 -0.167 -1.000 -1.000
## 2 -1 -1 -1 -0.813 -0.671 -0.809 -0.887 -0.671 -0.853 -1.000 -1.000 -0.774
## 3 -1 -1 -1 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.996 0.147 1.000
## 4 -1 -1 -1 -1.000 -1.000 -0.273 0.684 0.960 0.450 -0.067 -0.679 -1.000
## 5 -1 -1 -1 -1.000 -1.000 -0.928 -0.204 0.751 0.466 0.234 -0.809 -1.000
## 6 -1 -1 -1 -1.000 -1.000 -0.397 0.983 -0.535 -1.000 -1.000 -1.000 -1.000
## V14 V15 V16 V17 V18 V19 V20 V21 V22 V23 V24 V25
## 1 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000 -1.000 -1.000 -0.992 0.297
## 2 -0.180 0.052 -0.241 -1 -1 -1 -1 0.392 1.000 0.857 0.727 1.000
## 3 -0.189 -1.000 -1.000 -1 -1 -1 -1 -1.000 -1.000 -1.000 -1.000 -1.000
## 4 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000 -0.114 0.974 0.917 0.734
## 5 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000 -0.370 0.739 1.000 1.000
## 6 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000 -1.000 0.692 0.536 -0.767
## V26 V27 V28 V29 V30 V31 V32 V33 V34 V35 V36 V37
## 1 1.000 0.307 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 2 0.805 0.613 0.613 0.860 1.000 1.000 0.396 -1 -1 -1 -1 -0.548
## 3 -1.000 -0.882 1.000 0.390 -0.811 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 4 0.994 1.000 0.973 0.391 -0.421 -0.976 -1.000 -1 -1 -1 -1 -0.323
## 5 1.000 1.000 0.644 -0.890 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 6 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000
## V38 V39 V40 V41 V42 V43 V44 V45 V46 V47 V48
## 1 -1.000 -1.000 -0.410 1.000 0.986 -0.565 -1.000 -1.000 -1 -1.000 -1.000
## 2 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1 1.000 0.875
## 3 -1.000 -1.000 -1.000 -1.000 -1.000 -0.715 1.000 0.029 -1 -1.000 -1.000
## 4 0.991 0.622 -0.738 -1.000 -0.639 0.023 0.871 1.000 1 -0.432 -1.000
## 5 0.616 1.000 0.688 -0.455 -0.731 0.659 1.000 -0.287 -1 -1.000 -1.000
## 6 -0.921 0.928 -0.118 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1.000 -1.000
## V49 V50 V51 V52 V53 V54 V55 V56 V57 V58 V59 V60
## 1 -1.000 -1 -1 -1 -1.000 -1.000 -0.683 0.825 1 0.562 -1.000 -1.000
## 2 -0.957 -1 -1 -1 -0.786 0.961 1.000 1.000 1 0.727 0.403 0.403
## 3 -1.000 -1 -1 -1 -1.000 -0.888 -0.912 -1.000 -1 -1.000 -0.549 1.000
## 4 -1.000 -1 -1 -1 0.409 1.000 0.000 -1.000 -1 -1.000 -1.000 -0.842
## 5 -1.000 -1 -1 -1 -1.000 -0.376 -0.186 -0.874 -1 -1.000 -0.014 1.000
## 6 -1.000 -1 -1 -1 -1.000 -0.394 1.000 -0.596 -1 -1.000 -1.000 -1.000
## V61 V62 V63 V64 V65 V66 V67 V68 V69 V70 V71 V72
## 1 -1.000 -1.000 -1.000 -1.00 -1 -1 -1 -1.000 -1.000 -0.938 0.540 1.000
## 2 0.171 -0.314 -0.314 -0.94 -1 -1 -1 -1.000 -0.298 1.000 1.000 1.000
## 3 0.361 -1.000 -1.000 -1.00 -1 -1 -1 -1.000 -0.938 0.694 0.057 -1.000
## 4 0.714 1.000 -0.534 -1.00 -1 -1 -1 -0.879 0.965 1.000 -0.713 -1.000
## 5 -0.253 -1.000 -1.000 -1.00 -1 -1 -1 -1.000 -1.000 -1.000 -1.000 -1.000
## 6 -1.000 -1.000 -1.000 -1.00 -1 -1 -1 -1.000 -1.000 0.060 0.900 -0.951
## V73 V74 V75 V76 V77 V78 V79 V80 V81 V82 V83 V84
## 1 0.778 -0.715 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 2 0.440 0.056 -0.755 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 3 -1.000 -1.000 -0.382 1.000 0.511 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 4 -1.000 -1.000 -1.000 -0.606 0.977 0.695 -0.906 -1 -1 -1 -1 -0.528
## 5 -1.000 -0.978 0.501 1.000 -0.540 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 6 -1.000 -1.000 -1.000 -0.647 0.455 -0.333 -1.000 -1 -1 -1 -1 -1.000
## V85 V86 V87 V88 V89 V90 V91 V92 V93 V94 V95 V96
## 1 -1.000 0.100 1.000 0.922 -0.439 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1
## 2 0.366 1.000 1.000 1.000 1.000 1.000 0.889 -0.081 -0.920 -1.000 -1 -1
## 3 -0.311 1.000 -0.043 -1.000 -1.000 -1.000 -0.648 1.000 0.644 -1.000 -1 -1
## 4 1.000 0.931 -0.888 -1.000 -1.000 -1.000 -0.949 0.559 0.984 -0.363 -1 -1
## 5 -1.000 -1.000 -0.998 -0.341 0.296 0.371 1.000 0.417 -0.989 -1.000 -1 -1
## 6 -1.000 0.259 0.676 -1.000 -1.000 -1.000 -0.984 0.677 0.981 0.551 -1 -1
## V97 V98 V99 V100 V101 V102 V103 V104 V105 V106 V107 V108
## 1 -1 -1 -1 -1.00 -0.257 0.950 1.000 -0.162 -1.000 -1.00 -1.000 -0.987
## 2 -1 -1 -1 -1.00 -0.396 0.886 0.974 0.851 0.851 0.95 1.000 1.000
## 3 -1 -1 -1 -1.00 0.489 1.000 -0.493 -1.000 -1.000 -1.00 -0.564 1.000
## 4 -1 -1 -1 -0.97 -0.266 -0.555 -1.000 -1.000 -1.000 -1.00 -0.186 1.000
## 5 -1 -1 -1 -1.00 -1.000 -1.000 -0.008 1.000 1.000 1.00 1.000 0.761
## 6 -1 -1 -1 -1.00 -0.994 0.699 0.305 -1.000 -1.000 -1.00 -0.499 1.000
## V109 V110 V111 V112 V113 V114 V115 V116 V117 V118 V119 V120
## 1 -0.714 -0.832 -1 -1 -1 -1 -1 -0.797 0.909 1.000 0.300 -0.961
## 2 0.539 -0.754 -1 -1 -1 -1 -1 -1.000 -1.000 -0.886 -0.505 -1.000
## 3 0.693 -1.000 -1 -1 -1 -1 -1 -0.966 0.988 1.000 -0.893 -1.000
## 4 0.488 -1.000 -1 -1 -1 -1 -1 -1.000 -1.000 -1.000 -1.000 -1.000
## 5 -0.731 -1.000 -1 -1 -1 -1 -1 -1.000 -1.000 -1.000 0.242 1.000
## 6 -0.092 0.751 -1 -1 -1 -1 -1 -1.000 -0.923 0.966 -0.107 -1.000
## V121 V122 V123 V124 V125 V126 V127 V128 V129 V130 V131 V132
## 1 -1 -1.000 -0.550 0.485 0.996 0.867 0.092 -1 -1 -1 -1 0.278
## 2 -1 -0.649 0.405 1.000 1.000 0.653 -0.838 -1 -1 -1 -1 -1.000
## 3 -1 -1.000 -0.397 1.000 0.903 -0.977 -1.000 -1 -1 -1 -1 -0.559
## 4 -1 -1.000 0.697 0.992 -0.458 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 5 1 0.319 0.259 1.000 0.742 -0.757 -1.000 -1 -1 -1 -1 -1.000
## 6 -1 -1.000 -0.300 0.854 -0.382 0.617 -1.000 -1 -1 -1 -1 -1.000
## V133 V134 V135 V136 V137 V138 V139 V140 V141 V142 V143
## 1 1.000 0.877 -0.824 -1.000 -0.905 0.145 0.977 1.000 1.000 1.000 0.990
## 2 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.550 0.993 1.000 0.618
## 3 1.000 1.000 -0.297 -1.000 -1.000 -1.000 -0.611 1.000 0.873 -0.698 -0.552
## 4 -1.000 -1.000 -1.000 -1.000 -1.000 -0.341 1.000 0.608 -1.000 -1.000 -1.000
## 5 -1.000 -1.000 -0.975 -0.467 -0.989 -1.000 -1.000 -0.171 0.998 0.669 -0.945
## 6 -0.409 1.000 -0.529 -1.000 -1.000 -1.000 0.048 0.614 -0.268 0.544 -1.000
## V144 V145 V146 V147 V148 V149 V150 V151 V152 V153 V154
## 1 -0.745 -1 -1.00 -0.950 0.847 1.000 0.327 -1.000 -1.000 0.355 1.000
## 2 -0.869 -1 -0.96 -0.512 0.134 -0.343 -0.796 -1.000 -1.000 -1.000 -1.000
## 3 -1.000 -1 -1.00 -1.000 -0.126 1.000 1.000 0.766 -0.764 -1.000 -1.000
## 4 -1.000 -1 -1.00 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 0.471
## 5 -1.000 -1 -1.00 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000
## 6 -1.000 -1 -1.00 -1.000 -1.000 0.050 0.971 -0.839 -1.000 -1.000 -1.000
## V155 V156 V157 V158 V159 V160 V161 V162 V163 V164 V165
## 1 0.655 -0.109 -0.185 1.000 0.988 -0.723 -1 -1.000 -0.63 1.000 1.000
## 2 -1.000 -1.000 -0.432 0.994 1.000 0.223 -1 0.426 1.00 1.000 1.000
## 3 -0.577 1.000 0.933 0.484 -0.197 -1.000 -1 -1.000 -1.00 -0.818 -0.355
## 4 0.998 -0.416 -1.000 -1.000 -1.000 -1.000 -1 -1.000 -1.00 -1.000 -1.000
## 5 -1.000 -1.000 0.228 1.000 0.038 -1.000 -1 -1.000 -1.00 -1.000 -1.000
## 6 0.172 0.526 -0.003 0.307 -1.000 -1.000 -1 -1.000 -1.00 -1.000 0.398
## V166 V167 V168 V169 V170 V171 V172 V173 V174 V175 V176
## 1 0.068 -0.925 0.113 0.960 0.308 -0.884 -1.000 -0.075 1.000 0.641 -0.995
## 2 0.214 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 0.292 1.000 0.967
## 3 0.334 1.000 0.868 -0.289 -0.677 -0.596 1.000 1.000 1.000 -0.581 -1.000
## 4 -1.000 -1.000 -1.000 -0.644 0.963 0.590 -0.999 -1.000 -1.000 -1.000 -1.000
## 5 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.826 0.918 0.933 -0.794
## 6 0.459 -1.000 -1.000 -1.000 -1.000 0.372 0.555 0.520 -0.045 -1.000 -1.000
## V177 V178 V179 V180 V181 V182 V183 V184 V185 V186 V187
## 1 -1.00 -1.000 -0.677 1.000 1.000 0.753 0.341 1 0.707 -0.942 -1.000
## 2 -0.88 0.449 1.000 0.896 -0.094 -0.750 -1.000 -1 -1.000 -1.000 -1.000
## 3 -1.00 -1.000 -1.000 -1.000 -1.000 -0.954 0.118 1 1.000 1.000 1.000
## 4 -1.00 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1 0.061 1.000 -0.079
## 5 -1.00 -1.000 -1.000 -0.666 0.337 0.224 -0.908 -1 -1.000 -1.000 -1.000
## 6 -1.00 -1.000 -1.000 -1.000 0.671 0.176 -1.000 -1 -1.000 -1.000 0.236
## V188 V189 V190 V191 V192 V193 V194 V195 V196 V197 V198
## 1 -1.000 0.545 1.000 0.027 -1.000 -1.000 -1.000 -0.903 0.792 1.000 1.000
## 2 -1.000 -1.000 -0.627 1.000 1.000 0.198 -0.105 1.000 1.000 1.000 0.639
## 3 1.000 0.973 -0.092 -0.995 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000
## 4 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000
## 5 -1.000 -1.000 0.418 1.000 -0.258 -1.000 -1.000 -0.246 1.000 1.000 0.355
## 6 0.934 0.971 -0.712 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 0.763 0.084
## V199 V200 V201 V202 V203 V204 V205 V206 V207 V208 V209
## 1 1.000 1.000 0.536 0.184 0.812 0.837 0.978 0.864 -0.630 -1.000 -1.000
## 2 -0.168 -0.314 -0.446 -1.000 -1.000 -0.999 -0.337 0.147 0.996 1.000 0.667
## 3 -0.993 -0.464 0.046 0.290 0.457 1.000 0.721 -1.000 -1.000 -1.000 -1.000
## 4 -1.000 -1.000 0.773 0.958 -0.714 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000
## 5 -0.958 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.077 1.000 0.344 -1.000
## 6 -1.000 -1.000 -1.000 -1.000 0.073 1.000 0.265 -1.000 -1.000 -1.000 -1.000
## V210 V211 V212 V213 V214 V215 V216 V217 V218 V219 V220
## 1 -1.000 -1.000 -0.452 0.828 1.000 1.000 1.000 1.000 1.000 1.000 1.000
## 2 -0.808 0.065 0.993 1.000 1.000 1.000 1.000 0.996 0.970 0.970 0.970
## 3 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.426 1.000
## 4 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.545 0.989 0.432 -1.000 -1.000
## 5 -1.000 0.075 1.000 1.000 0.649 0.256 -0.200 -0.351 -0.733 -0.733 -0.733
## 6 -1.000 -1.000 -1.000 0.563 0.210 -1.000 -1.000 -0.930 -0.127 0.890 0.935
## V221 V222 V223 V224 V225 V226 V227 V228 V229 V230 V231
## 1 1.000 0.135 -1 -1.000 -1.000 -1 -1.000 -1.000 -0.483 0.813 1.000
## 2 0.998 1.000 1 1.000 0.109 -1 -1.000 -0.830 -0.242 0.350 0.800
## 3 0.555 -1.000 -1 -1.000 -1.000 -1 -1.000 -1.000 -1.000 -1.000 -1.000
## 4 -1.000 -1.000 -1 -1.000 -1.000 -1 -1.000 -1.000 -1.000 -1.000 -1.000
## 5 -0.433 0.649 1 0.093 -1.000 -1 -0.959 -0.062 0.821 1.000 1.000
## 6 -0.845 -1.000 -1 -1.000 -1.000 -1 -1.000 -1.000 0.093 0.793 -0.205
## V232 V233 V234 V235 V236 V237 V238 V239 V240 V241 V242
## 1 1.000 1.000 1.000 1.000 1.000 0.219 -0.943 -1.000 -1.000 -1.00 -1
## 2 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 0.616 -0.93 -1
## 3 -1.000 -1.000 -1.000 0.024 1.000 0.388 -1.000 -1.000 -1.000 -1.00 -1
## 4 -0.348 1.000 0.798 -0.935 -1.000 -1.000 -1.000 -1.000 -1.000 -1.00 -1
## 5 1.000 1.000 1.000 1.000 1.000 1.000 1.000 0.583 -0.843 -1.00 -1
## 6 0.214 0.746 0.918 0.692 0.954 -0.882 -1.000 -1.000 -1.000 -1.00 -1
## V243 V244 V245 V246 V247 V248 V249 V250 V251 V252 V253
## 1 -1 -1 -1.000 -0.974 -0.429 0.304 0.823 1.000 0.482 -0.474 -0.991
## 2 -1 -1 -1.000 -1.000 -0.858 -0.671 -0.671 -0.033 0.761 0.762 0.126
## 3 -1 -1 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.109 1.000 -0.179
## 4 -1 -1 -1.000 -1.000 -1.000 -0.318 1.000 0.536 -0.987 -1.000 -1.000
## 5 -1 -1 -0.877 -0.326 0.174 0.466 0.639 1.000 1.000 0.791 0.439
## 6 -1 -1 -0.898 0.323 1.000 0.803 0.015 -0.862 -0.871 -0.437 -1.000
## V254 V255 V256 V257
## 1 -1.000 -1.000 -1.000 -1
## 2 -0.095 -0.671 -0.828 -1
## 3 -1.000 -1.000 -1.000 -1
## 4 -1.000 -1.000 -1.000 -1
## 5 -0.199 -0.883 -1.000 -1
## 6 -1.000 -1.000 -1.000 -1y <- taprendizaje$Numerodatos.test <- model.matrix(Numero~.,ttesting)[,-1]
modelo.lasso <- glmnet(x, y, alpha = 1, family = "multinomial")
plot(modelo.lasso,"lambda", label=TRUE)
modelo.lasso.cv <- cv.glmnet(x, y, alpha = 1, family = "multinomial")mejor.lambda <- modelo.lasso.cv$lambda.min
mejor.lambda## [1] 0.0005928984prediccion <- predict(modelo.lasso.cv,datos.test,type="class",s=mejor.lambda)
Actual <- ttesting$Numero
## Matriz de Confusión
MC <- table(Actual, prediccion)
# Índices de Calidad de la predicción
indices.general(MC)## $`Matriz de Confusión`
## prediccion
## Actual cero cinco cuatro dos nueve ocho seis siete tres uno
## cero 314 1 2 1 1 1 0 0 1 0
## cinco 2 115 0 1 1 1 2 0 5 0
## cuatro 0 0 147 1 4 1 1 1 0 3
## dos 1 0 3 186 0 2 1 0 3 0
## nueve 0 0 2 1 148 0 0 5 0 0
## ocho 4 3 0 2 0 125 0 0 6 0
## seis 3 0 0 3 0 0 140 0 0 0
## siete 0 2 5 1 6 1 0 153 1 0
## tres 3 6 1 6 1 8 0 2 155 0
## uno 0 1 1 0 1 0 1 0 1 259
##
## $`Precisión Global`
## [1] 0.9370629
##
## $`Error Global`
## [1] 0.06293706
##
## $`Precisión por categoría`
## cero cinco cuatro dos nueve ocho seis siete
## 0.9781931 0.9055118 0.9303797 0.9489796 0.9487179 0.8928571 0.9589041 0.9053254
## tres uno
## 0.8516484 0.9810606
##
## $`Precision Positiva`
## [1] 0.982906
##
## $`Precision Negativa`
## [1] 0.9968254
##
## $`Falsos Positivos`
## [1] 0.003174603
##
## $`Falsos Negativos`
## [1] 0.01709402
##
## $`Asertividad Positiva`
## [1] 0.9913793
##
## $`Asertividad Negativa`
## [1] 0.9936709###Ridge
x <- model.matrix(Numero ~ ., taprendizaje)[,-1]
head(x)## V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13
## 1 -1 -1 -1 -1.000 -1.000 -1.000 -1.000 -0.631 0.862 -0.167 -1.000 -1.000
## 2 -1 -1 -1 -0.813 -0.671 -0.809 -0.887 -0.671 -0.853 -1.000 -1.000 -0.774
## 3 -1 -1 -1 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.996 0.147 1.000
## 4 -1 -1 -1 -1.000 -1.000 -0.273 0.684 0.960 0.450 -0.067 -0.679 -1.000
## 5 -1 -1 -1 -1.000 -1.000 -0.928 -0.204 0.751 0.466 0.234 -0.809 -1.000
## 6 -1 -1 -1 -1.000 -1.000 -0.397 0.983 -0.535 -1.000 -1.000 -1.000 -1.000
## V14 V15 V16 V17 V18 V19 V20 V21 V22 V23 V24 V25
## 1 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000 -1.000 -1.000 -0.992 0.297
## 2 -0.180 0.052 -0.241 -1 -1 -1 -1 0.392 1.000 0.857 0.727 1.000
## 3 -0.189 -1.000 -1.000 -1 -1 -1 -1 -1.000 -1.000 -1.000 -1.000 -1.000
## 4 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000 -0.114 0.974 0.917 0.734
## 5 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000 -0.370 0.739 1.000 1.000
## 6 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000 -1.000 0.692 0.536 -0.767
## V26 V27 V28 V29 V30 V31 V32 V33 V34 V35 V36 V37
## 1 1.000 0.307 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 2 0.805 0.613 0.613 0.860 1.000 1.000 0.396 -1 -1 -1 -1 -0.548
## 3 -1.000 -0.882 1.000 0.390 -0.811 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 4 0.994 1.000 0.973 0.391 -0.421 -0.976 -1.000 -1 -1 -1 -1 -0.323
## 5 1.000 1.000 0.644 -0.890 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 6 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000
## V38 V39 V40 V41 V42 V43 V44 V45 V46 V47 V48
## 1 -1.000 -1.000 -0.410 1.000 0.986 -0.565 -1.000 -1.000 -1 -1.000 -1.000
## 2 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1 1.000 0.875
## 3 -1.000 -1.000 -1.000 -1.000 -1.000 -0.715 1.000 0.029 -1 -1.000 -1.000
## 4 0.991 0.622 -0.738 -1.000 -0.639 0.023 0.871 1.000 1 -0.432 -1.000
## 5 0.616 1.000 0.688 -0.455 -0.731 0.659 1.000 -0.287 -1 -1.000 -1.000
## 6 -0.921 0.928 -0.118 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1.000 -1.000
## V49 V50 V51 V52 V53 V54 V55 V56 V57 V58 V59 V60
## 1 -1.000 -1 -1 -1 -1.000 -1.000 -0.683 0.825 1 0.562 -1.000 -1.000
## 2 -0.957 -1 -1 -1 -0.786 0.961 1.000 1.000 1 0.727 0.403 0.403
## 3 -1.000 -1 -1 -1 -1.000 -0.888 -0.912 -1.000 -1 -1.000 -0.549 1.000
## 4 -1.000 -1 -1 -1 0.409 1.000 0.000 -1.000 -1 -1.000 -1.000 -0.842
## 5 -1.000 -1 -1 -1 -1.000 -0.376 -0.186 -0.874 -1 -1.000 -0.014 1.000
## 6 -1.000 -1 -1 -1 -1.000 -0.394 1.000 -0.596 -1 -1.000 -1.000 -1.000
## V61 V62 V63 V64 V65 V66 V67 V68 V69 V70 V71 V72
## 1 -1.000 -1.000 -1.000 -1.00 -1 -1 -1 -1.000 -1.000 -0.938 0.540 1.000
## 2 0.171 -0.314 -0.314 -0.94 -1 -1 -1 -1.000 -0.298 1.000 1.000 1.000
## 3 0.361 -1.000 -1.000 -1.00 -1 -1 -1 -1.000 -0.938 0.694 0.057 -1.000
## 4 0.714 1.000 -0.534 -1.00 -1 -1 -1 -0.879 0.965 1.000 -0.713 -1.000
## 5 -0.253 -1.000 -1.000 -1.00 -1 -1 -1 -1.000 -1.000 -1.000 -1.000 -1.000
## 6 -1.000 -1.000 -1.000 -1.00 -1 -1 -1 -1.000 -1.000 0.060 0.900 -0.951
## V73 V74 V75 V76 V77 V78 V79 V80 V81 V82 V83 V84
## 1 0.778 -0.715 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 2 0.440 0.056 -0.755 -1.000 -1.000 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 3 -1.000 -1.000 -0.382 1.000 0.511 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 4 -1.000 -1.000 -1.000 -0.606 0.977 0.695 -0.906 -1 -1 -1 -1 -0.528
## 5 -1.000 -0.978 0.501 1.000 -0.540 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 6 -1.000 -1.000 -1.000 -0.647 0.455 -0.333 -1.000 -1 -1 -1 -1 -1.000
## V85 V86 V87 V88 V89 V90 V91 V92 V93 V94 V95 V96
## 1 -1.000 0.100 1.000 0.922 -0.439 -1.000 -1.000 -1.000 -1.000 -1.000 -1 -1
## 2 0.366 1.000 1.000 1.000 1.000 1.000 0.889 -0.081 -0.920 -1.000 -1 -1
## 3 -0.311 1.000 -0.043 -1.000 -1.000 -1.000 -0.648 1.000 0.644 -1.000 -1 -1
## 4 1.000 0.931 -0.888 -1.000 -1.000 -1.000 -0.949 0.559 0.984 -0.363 -1 -1
## 5 -1.000 -1.000 -0.998 -0.341 0.296 0.371 1.000 0.417 -0.989 -1.000 -1 -1
## 6 -1.000 0.259 0.676 -1.000 -1.000 -1.000 -0.984 0.677 0.981 0.551 -1 -1
## V97 V98 V99 V100 V101 V102 V103 V104 V105 V106 V107 V108
## 1 -1 -1 -1 -1.00 -0.257 0.950 1.000 -0.162 -1.000 -1.00 -1.000 -0.987
## 2 -1 -1 -1 -1.00 -0.396 0.886 0.974 0.851 0.851 0.95 1.000 1.000
## 3 -1 -1 -1 -1.00 0.489 1.000 -0.493 -1.000 -1.000 -1.00 -0.564 1.000
## 4 -1 -1 -1 -0.97 -0.266 -0.555 -1.000 -1.000 -1.000 -1.00 -0.186 1.000
## 5 -1 -1 -1 -1.00 -1.000 -1.000 -0.008 1.000 1.000 1.00 1.000 0.761
## 6 -1 -1 -1 -1.00 -0.994 0.699 0.305 -1.000 -1.000 -1.00 -0.499 1.000
## V109 V110 V111 V112 V113 V114 V115 V116 V117 V118 V119 V120
## 1 -0.714 -0.832 -1 -1 -1 -1 -1 -0.797 0.909 1.000 0.300 -0.961
## 2 0.539 -0.754 -1 -1 -1 -1 -1 -1.000 -1.000 -0.886 -0.505 -1.000
## 3 0.693 -1.000 -1 -1 -1 -1 -1 -0.966 0.988 1.000 -0.893 -1.000
## 4 0.488 -1.000 -1 -1 -1 -1 -1 -1.000 -1.000 -1.000 -1.000 -1.000
## 5 -0.731 -1.000 -1 -1 -1 -1 -1 -1.000 -1.000 -1.000 0.242 1.000
## 6 -0.092 0.751 -1 -1 -1 -1 -1 -1.000 -0.923 0.966 -0.107 -1.000
## V121 V122 V123 V124 V125 V126 V127 V128 V129 V130 V131 V132
## 1 -1 -1.000 -0.550 0.485 0.996 0.867 0.092 -1 -1 -1 -1 0.278
## 2 -1 -0.649 0.405 1.000 1.000 0.653 -0.838 -1 -1 -1 -1 -1.000
## 3 -1 -1.000 -0.397 1.000 0.903 -0.977 -1.000 -1 -1 -1 -1 -0.559
## 4 -1 -1.000 0.697 0.992 -0.458 -1.000 -1.000 -1 -1 -1 -1 -1.000
## 5 1 0.319 0.259 1.000 0.742 -0.757 -1.000 -1 -1 -1 -1 -1.000
## 6 -1 -1.000 -0.300 0.854 -0.382 0.617 -1.000 -1 -1 -1 -1 -1.000
## V133 V134 V135 V136 V137 V138 V139 V140 V141 V142 V143
## 1 1.000 0.877 -0.824 -1.000 -0.905 0.145 0.977 1.000 1.000 1.000 0.990
## 2 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.550 0.993 1.000 0.618
## 3 1.000 1.000 -0.297 -1.000 -1.000 -1.000 -0.611 1.000 0.873 -0.698 -0.552
## 4 -1.000 -1.000 -1.000 -1.000 -1.000 -0.341 1.000 0.608 -1.000 -1.000 -1.000
## 5 -1.000 -1.000 -0.975 -0.467 -0.989 -1.000 -1.000 -0.171 0.998 0.669 -0.945
## 6 -0.409 1.000 -0.529 -1.000 -1.000 -1.000 0.048 0.614 -0.268 0.544 -1.000
## V144 V145 V146 V147 V148 V149 V150 V151 V152 V153 V154
## 1 -0.745 -1 -1.00 -0.950 0.847 1.000 0.327 -1.000 -1.000 0.355 1.000
## 2 -0.869 -1 -0.96 -0.512 0.134 -0.343 -0.796 -1.000 -1.000 -1.000 -1.000
## 3 -1.000 -1 -1.00 -1.000 -0.126 1.000 1.000 0.766 -0.764 -1.000 -1.000
## 4 -1.000 -1 -1.00 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 0.471
## 5 -1.000 -1 -1.00 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000
## 6 -1.000 -1 -1.00 -1.000 -1.000 0.050 0.971 -0.839 -1.000 -1.000 -1.000
## V155 V156 V157 V158 V159 V160 V161 V162 V163 V164 V165
## 1 0.655 -0.109 -0.185 1.000 0.988 -0.723 -1 -1.000 -0.63 1.000 1.000
## 2 -1.000 -1.000 -0.432 0.994 1.000 0.223 -1 0.426 1.00 1.000 1.000
## 3 -0.577 1.000 0.933 0.484 -0.197 -1.000 -1 -1.000 -1.00 -0.818 -0.355
## 4 0.998 -0.416 -1.000 -1.000 -1.000 -1.000 -1 -1.000 -1.00 -1.000 -1.000
## 5 -1.000 -1.000 0.228 1.000 0.038 -1.000 -1 -1.000 -1.00 -1.000 -1.000
## 6 0.172 0.526 -0.003 0.307 -1.000 -1.000 -1 -1.000 -1.00 -1.000 0.398
## V166 V167 V168 V169 V170 V171 V172 V173 V174 V175 V176
## 1 0.068 -0.925 0.113 0.960 0.308 -0.884 -1.000 -0.075 1.000 0.641 -0.995
## 2 0.214 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 0.292 1.000 0.967
## 3 0.334 1.000 0.868 -0.289 -0.677 -0.596 1.000 1.000 1.000 -0.581 -1.000
## 4 -1.000 -1.000 -1.000 -0.644 0.963 0.590 -0.999 -1.000 -1.000 -1.000 -1.000
## 5 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.826 0.918 0.933 -0.794
## 6 0.459 -1.000 -1.000 -1.000 -1.000 0.372 0.555 0.520 -0.045 -1.000 -1.000
## V177 V178 V179 V180 V181 V182 V183 V184 V185 V186 V187
## 1 -1.00 -1.000 -0.677 1.000 1.000 0.753 0.341 1 0.707 -0.942 -1.000
## 2 -0.88 0.449 1.000 0.896 -0.094 -0.750 -1.000 -1 -1.000 -1.000 -1.000
## 3 -1.00 -1.000 -1.000 -1.000 -1.000 -0.954 0.118 1 1.000 1.000 1.000
## 4 -1.00 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1 0.061 1.000 -0.079
## 5 -1.00 -1.000 -1.000 -0.666 0.337 0.224 -0.908 -1 -1.000 -1.000 -1.000
## 6 -1.00 -1.000 -1.000 -1.000 0.671 0.176 -1.000 -1 -1.000 -1.000 0.236
## V188 V189 V190 V191 V192 V193 V194 V195 V196 V197 V198
## 1 -1.000 0.545 1.000 0.027 -1.000 -1.000 -1.000 -0.903 0.792 1.000 1.000
## 2 -1.000 -1.000 -0.627 1.000 1.000 0.198 -0.105 1.000 1.000 1.000 0.639
## 3 1.000 0.973 -0.092 -0.995 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000
## 4 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000
## 5 -1.000 -1.000 0.418 1.000 -0.258 -1.000 -1.000 -0.246 1.000 1.000 0.355
## 6 0.934 0.971 -0.712 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 0.763 0.084
## V199 V200 V201 V202 V203 V204 V205 V206 V207 V208 V209
## 1 1.000 1.000 0.536 0.184 0.812 0.837 0.978 0.864 -0.630 -1.000 -1.000
## 2 -0.168 -0.314 -0.446 -1.000 -1.000 -0.999 -0.337 0.147 0.996 1.000 0.667
## 3 -0.993 -0.464 0.046 0.290 0.457 1.000 0.721 -1.000 -1.000 -1.000 -1.000
## 4 -1.000 -1.000 0.773 0.958 -0.714 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000
## 5 -0.958 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.077 1.000 0.344 -1.000
## 6 -1.000 -1.000 -1.000 -1.000 0.073 1.000 0.265 -1.000 -1.000 -1.000 -1.000
## V210 V211 V212 V213 V214 V215 V216 V217 V218 V219 V220
## 1 -1.000 -1.000 -0.452 0.828 1.000 1.000 1.000 1.000 1.000 1.000 1.000
## 2 -0.808 0.065 0.993 1.000 1.000 1.000 1.000 0.996 0.970 0.970 0.970
## 3 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.426 1.000
## 4 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.545 0.989 0.432 -1.000 -1.000
## 5 -1.000 0.075 1.000 1.000 0.649 0.256 -0.200 -0.351 -0.733 -0.733 -0.733
## 6 -1.000 -1.000 -1.000 0.563 0.210 -1.000 -1.000 -0.930 -0.127 0.890 0.935
## V221 V222 V223 V224 V225 V226 V227 V228 V229 V230 V231
## 1 1.000 0.135 -1 -1.000 -1.000 -1 -1.000 -1.000 -0.483 0.813 1.000
## 2 0.998 1.000 1 1.000 0.109 -1 -1.000 -0.830 -0.242 0.350 0.800
## 3 0.555 -1.000 -1 -1.000 -1.000 -1 -1.000 -1.000 -1.000 -1.000 -1.000
## 4 -1.000 -1.000 -1 -1.000 -1.000 -1 -1.000 -1.000 -1.000 -1.000 -1.000
## 5 -0.433 0.649 1 0.093 -1.000 -1 -0.959 -0.062 0.821 1.000 1.000
## 6 -0.845 -1.000 -1 -1.000 -1.000 -1 -1.000 -1.000 0.093 0.793 -0.205
## V232 V233 V234 V235 V236 V237 V238 V239 V240 V241 V242
## 1 1.000 1.000 1.000 1.000 1.000 0.219 -0.943 -1.000 -1.000 -1.00 -1
## 2 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000 0.616 -0.93 -1
## 3 -1.000 -1.000 -1.000 0.024 1.000 0.388 -1.000 -1.000 -1.000 -1.00 -1
## 4 -0.348 1.000 0.798 -0.935 -1.000 -1.000 -1.000 -1.000 -1.000 -1.00 -1
## 5 1.000 1.000 1.000 1.000 1.000 1.000 1.000 0.583 -0.843 -1.00 -1
## 6 0.214 0.746 0.918 0.692 0.954 -0.882 -1.000 -1.000 -1.000 -1.00 -1
## V243 V244 V245 V246 V247 V248 V249 V250 V251 V252 V253
## 1 -1 -1 -1.000 -0.974 -0.429 0.304 0.823 1.000 0.482 -0.474 -0.991
## 2 -1 -1 -1.000 -1.000 -0.858 -0.671 -0.671 -0.033 0.761 0.762 0.126
## 3 -1 -1 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -0.109 1.000 -0.179
## 4 -1 -1 -1.000 -1.000 -1.000 -0.318 1.000 0.536 -0.987 -1.000 -1.000
## 5 -1 -1 -0.877 -0.326 0.174 0.466 0.639 1.000 1.000 0.791 0.439
## 6 -1 -1 -0.898 0.323 1.000 0.803 0.015 -0.862 -0.871 -0.437 -1.000
## V254 V255 V256 V257
## 1 -1.000 -1.000 -1.000 -1
## 2 -0.095 -0.671 -0.828 -1
## 3 -1.000 -1.000 -1.000 -1
## 4 -1.000 -1.000 -1.000 -1
## 5 -0.199 -0.883 -1.000 -1
## 6 -1.000 -1.000 -1.000 -1y <- taprendizaje$Numerolibrary(glmnet)
datos.test <- model.matrix(Numero~.,ttesting)[,-1]
modelo.ridge <- glmnet(x, y, alpha = 1, family = "multinomial")
plot(modelo.ridge,"lambda", label=TRUE)
modelo.ridge.cv <- cv.glmnet(x, y, alpha = 1, family = "multinomial")
plot(modelo.ridge.cv)
mejor.lambda <- modelo.ridge.cv$lambda.min
mejor.lambda## [1] 0.0005928984prediccion <- predict(modelo.ridge.cv,datos.test,type="class",s=mejor.lambda)
Actual <- ttesting$Numero
## Matriz de Confusión
MC <- table(Actual, prediccion)
# Índices de Calidad de la predicción
indices.general(MC)## $`Matriz de Confusión`
## prediccion
## Actual cero cinco cuatro dos nueve ocho seis siete tres uno
## cero 314 1 2 1 1 1 0 0 1 0
## cinco 2 115 0 1 1 1 2 0 5 0
## cuatro 0 0 147 1 4 1 1 1 0 3
## dos 1 0 3 186 0 2 1 0 3 0
## nueve 0 0 2 1 148 0 0 5 0 0
## ocho 4 3 0 2 0 125 0 0 6 0
## seis 3 0 0 3 0 0 140 0 0 0
## siete 0 2 5 1 6 1 0 153 1 0
## tres 3 6 1 6 1 8 0 2 155 0
## uno 0 1 1 0 1 0 1 0 1 259
##
## $`Precisión Global`
## [1] 0.9370629
##
## $`Error Global`
## [1] 0.06293706
##
## $`Precisión por categoría`
## cero cinco cuatro dos nueve ocho seis siete
## 0.9781931 0.9055118 0.9303797 0.9489796 0.9487179 0.8928571 0.9589041 0.9053254
## tres uno
## 0.8516484 0.9810606
##
## $`Precision Positiva`
## [1] 0.982906
##
## $`Precision Negativa`
## [1] 0.9968254
##
## $`Falsos Positivos`
## [1] 0.003174603
##
## $`Falsos Negativos`
## [1] 0.01709402
##
## $`Asertividad Positiva`
## [1] 0.9913793
##
## $`Asertividad Negativa`
## [1] 0.9936709- Compare los resultados con los obtenidos en las tareas anteriores
En este caso, los metodos de Ridge y Lasso, tienen precision global de 0.9386767 y 0.9472835, respectivamente, su precision por categoria es bastante buena es decir todos los valores en el caso de Lasso estan sobre 0,90 y en el caso de Ridge encima de 0,88. El caso de la logistica es opuesto, la estimacion no resulta buena con una precision de 0.2275417.Cabe indicar que en tareas pasadas han habido mejores resultados, una precision global en el caso de arboles aleatorios de 0.9601937 y el de XGBoosting de 0.958042, aunque el SVM radial tiene tambien precision global alta no distingue tan bien por categoria como estos metodos anteriores. Por ello resulta mejor tanto el bosques aleatorio como el XGboosting, al tener todos los numeros con precision por encima de 0,90. Con una precision global de 0.964497 el SVM radial es el que mejor estima la variabilidad del modelo. El SVM ademas de tener una precision global alta, tambien tiene una precision por categoria bastante elevada en todos los numeros aunque no tan optima como estos dos metodos anteriores, a diferencia de los otros metodos. Es decir kvecinos tambien tuvo una precision global alta pero no es preciso con todos los numeros por igual. Debe senalarse que de los modelos anteriores el de arboles de decision tambien tiene mal desempeno, igual que bayes. A pesar de ello, puede senalarse la red neuronal tanto nnet como neuralnet tardan mucho en procesar los datos, mucho mas que en el caso de los kvecinos, por lo que, para el uso de equipo con baja capacidad de procesamiento puede resultar mas optimo SVM o incluso kvencinos. En el caso de los kvecinos se obtuvo precision global de 0.9585799, aun con kvecinos es superior que con la aproximacion de redes nnet (0.8682087).